diff --git "a/profile_trace/iteration_32768/rank0_trace.json" "b/profile_trace/iteration_32768/rank0_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_32768/rank0_trace.json" @@ -0,0 +1,157273 @@ + +{ + "schemaVersion": 1, + "deviceProperties": [ + { + "id": 0, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 1, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 2, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 3, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 4, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 5, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 6, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 7, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + } + ], + "cupti_version": 22, + "cuda_runtime_version": 12040, + "cuda_driver_version": 12080, + "distributedInfo": {"backend": "nccl", "rank": 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": "694D2C5BED0244E08B1C75E2C0E177F6", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850769044.029, "dur": 203.390, + "args": { + "External id": 1430017,"Record function id": 0, "Sequence number": 15348884, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850769127.674, "dur": 106.787, + "args": { + "External id": 1430018,"Sequence number": 15348884, "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": 2338706, "tid": 2379422, "ts": 6413850769127.674, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2379422, + "ts": 6413850769138.270, "dur": 93.587, + "args": { + "External id": 1430019,"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": 2338706, "tid": 2379422, + "ts": 6413850769268.406, "dur": 303.931, + "args": { + "External id": 1430020,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850769345.281, "dur": 120.397, + "args": { + "External id": 1430021,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 2338706, "tid": 2379422, + "ts": 6413850769383.650, "dur": 64.875, + "args": { + "External id": 1430022,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850769473.469, "dur": 2.113, + "args": { + "External id": 1430023,"Sequence number": 15348883, "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": 2338706, "tid": 2379422, "ts": 6413850769473.469, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850769481.668, "dur": 83.257, + "args": { + "External id": 1430024,"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": 2338706, "tid": 2379422, + "ts": 6413850769506.371, "dur": 57.871, + "args": { + "External id": 1430025,"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": 2338706, "tid": 2379422, + "ts": 6413850769519.277, "dur": 5.222, + "args": { + "External id": 1430026,"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": 2338706, "tid": 2379422, + "ts": 6413850769585.308, "dur": 37877.304, + "args": { + "External id": 1430027,"Record function id": 0, "Sequence number": 15348881, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850769587.585, "dur": 37855.696, + "args": { + "External id": 1430028,"Sequence number": 15348881, "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": 2338706, "tid": 2379422, "ts": 6413850769587.585, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850769639.503, "dur": 5.864, + "args": { + "External id": 1430029,"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": 2338706, "tid": 2379422, + "ts": 6413850769650.252, "dur": 37458.924, + "args": { + "External id": 1430030,"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": 2338706, "tid": 2379422, + "ts": 6413850769655.914, "dur": 37452.751, + "args": { + "External id": 1430031,"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": 2338706, "tid": 2379422, + "ts": 6413850769662.784, "dur": 9.183, + "args": { + "External id": 1430032,"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": 2338706, "tid": 2379422, + "ts": 6413850769675.155, "dur": 37431.274, + "args": { + "External id": 1430033,"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": 2338706, "tid": 2379422, + "ts": 6413850807116.839, "dur": 0.743, + "args": { + "External id": 1430034,"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": 2338706, "tid": 2379422, + "ts": 6413850807121.178, "dur": 3.700, + "args": { + "External id": 1430035,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807122.818, "dur": 1.567, + "args": { + "External id": 1430036,"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": 2338706, "tid": 2379422, + "ts": 6413850807133.701, "dur": 39.457, + "args": { + "External id": 1430037,"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": 2338706, "tid": 2379422, + "ts": 6413850807184.100, "dur": 54.155, + "args": { + "External id": 1430038,"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": 2338706, "tid": 2379422, + "ts": 6413850807187.035, "dur": 50.990, + "args": { + "External id": 1430039,"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": 2338706, "tid": 2379422, + "ts": 6413850807188.680, "dur": 49.042, + "args": { + "External id": 1430040,"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": 2338706, "tid": 2379422, + "ts": 6413850807483.603, "dur": 27.340, + "args": { + "External id": 1430041,"Record function id": 0, "Sequence number": 15348880, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807486.987, "dur": 21.002, + "args": { + "External id": 1430042,"Sequence number": 15348880, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 25 + } + }, + { + "ph": "f", "id": 4, "pid": 2338706, "tid": 2379422, "ts": 6413850807486.987, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850807493.231, "dur": 14.472, + "args": { + "External id": 1430043,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 26 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850807499.650, "dur": 7.830, + "args": { + "External id": 1430044,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 27 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807517.965, "dur": 131.125, + "args": { + "External id": 1430045,"Record function id": 0, "Sequence number": 15348879, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807519.118, "dur": 122.283, + "args": { + "External id": 1430046,"Sequence number": 15348879, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 29 + } + }, + { + "ph": "f", "id": 5, "pid": 2338706, "tid": 2379422, "ts": 6413850807519.118, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850807523.545, "dur": 117.355, + "args": { + "External id": 1430047,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 30 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850807529.471, "dur": 46.793, + "args": { + "External id": 1430048,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 31 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850807536.111, "dur": 7.659, + "args": { + "External id": 1430049,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 32 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807545.232, "dur": 30.672, + "args": { + "External id": 1430050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 33 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807551.941, "dur": 23.455, + "args": { + "External id": 1430051,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 34 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850807578.961, "dur": 9.598, + "args": { + "External id": 1430052,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 35 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850807582.488, "dur": 5.626, + "args": { + "External id": 1430053,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 36 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807590.304, "dur": 49.367, + "args": { + "External id": 1430054,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 37 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807655.611, "dur": 79.848, + "args": { + "External id": 1430055,"Record function id": 0, "Sequence number": 15348878, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807656.951, "dur": 74.514, + "args": { + "External id": 1430056,"Sequence number": 15348878, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 39 + } + }, + { + "ph": "f", "id": 6, "pid": 2338706, "tid": 2379422, "ts": 6413850807656.951, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850807660.315, "dur": 70.870, + "args": { + "External id": 1430057,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 40 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850807665.920, "dur": 26.435, + "args": { + "External id": 1430058,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 41 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850807667.504, "dur": 4.338, + "args": { + "External id": 1430059,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 42 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807672.788, "dur": 19.252, + "args": { + "External id": 1430060,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 43 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807677.549, "dur": 14.027, + "args": { + "External id": 1430061,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 44 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850807694.478, "dur": 10.559, + "args": { + "External id": 1430062,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 45 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850807702.225, "dur": 1.346, + "args": { + "External id": 1430063,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 46 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807706.333, "dur": 24.038, + "args": { + "External id": 1430064,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 47 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807739.832, "dur": 264.840, + "args": { + "External id": 1430065,"Record function id": 0, "Sequence number": 15348877, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850807740.894, "dur": 256.781, + "args": { + "External id": 1430066,"Sequence number": 15348877, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 49 + } + }, + { + "ph": "f", "id": 7, "pid": 2338706, "tid": 2379422, "ts": 6413850807740.894, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850807745.979, "dur": 250.025, + "args": { + "External id": 1430067,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 50 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850807750.714, "dur": 20.688, + "args": { + "External id": 1430068,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 51 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850807751.588, "dur": 2.992, + "args": { + "External id": 1430069,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 52 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807755.587, "dur": 15.526, + "args": { + "External id": 1430070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 53 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807756.337, "dur": 14.283, + "args": { + "External id": 1430071,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 54 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850807772.597, "dur": 2.539, + "args": { + "External id": 1430072,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 55 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850807774.055, "dur": 0.882, + "args": { + "External id": 1430073,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 56 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850807779.332, "dur": 214.537, + "args": { + "External id": 1430074,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 57 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850808014.699, "dur": 151.465, + "args": { + "External id": 1430075,"Record function id": 0, "Sequence number": 15348876, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850808015.906, "dur": 143.347, + "args": { + "External id": 1430076,"Sequence number": 15348876, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 59 + } + }, + { + "ph": "f", "id": 8, "pid": 2338706, "tid": 2379422, "ts": 6413850808015.906, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850808018.155, "dur": 140.557, + "args": { + "External id": 1430077,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 60 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850808022.094, "dur": 23.572, + "args": { + "External id": 1430078,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 61 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850808023.170, "dur": 3.196, + "args": { + "External id": 1430079,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 62 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850808026.989, "dur": 18.366, + "args": { + "External id": 1430080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 63 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850808028.124, "dur": 16.796, + "args": { + "External id": 1430081,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 64 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850808046.699, "dur": 39.525, + "args": { + "External id": 1430082,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 65 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850808051.036, "dur": 0.955, + "args": { + "External id": 1430083,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 66 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850808088.795, "dur": 68.638, + "args": { + "External id": 1430084,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 67 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850808177.098, "dur": 52.745, + "args": { + "External id": 1430085,"Record function id": 0, "Sequence number": 15348875, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850808179.016, "dur": 1.472, + "args": { + "External id": 1430086,"Sequence number": 15348875, "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": 2338706, "tid": 2379422, "ts": 6413850808179.016, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850808183.815, "dur": 42.631, + "args": { + "External id": 1430087,"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": 2338706, "tid": 2379422, + "ts": 6413850808186.658, "dur": 39.318, + "args": { + "External id": 1430088,"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": 2338706, "tid": 2379422, + "ts": 6413850808199.439, "dur": 3.885, + "args": { + "External id": 1430089,"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": 2338706, "tid": 2379422, + "ts": 6413850808236.036, "dur": 2311.597, + "args": { + "External id": 1430090,"Record function id": 0, "Sequence number": 15348873, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850808237.816, "dur": 2268.318, + "args": { + "External id": 1430091,"Sequence number": 15348873, "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": 2338706, "tid": 2379422, "ts": 6413850808237.816, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850808283.077, "dur": 4.940, + "args": { + "External id": 1430092,"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": 2338706, "tid": 2379422, + "ts": 6413850808291.215, "dur": 1954.662, + "args": { + "External id": 1430093,"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": 2338706, "tid": 2379422, + "ts": 6413850808293.411, "dur": 1952.072, + "args": { + "External id": 1430094,"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": 2338706, "tid": 2379422, + "ts": 6413850808296.681, "dur": 7.645, + "args": { + "External id": 1430095,"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": 2338706, "tid": 2379422, + "ts": 6413850808305.372, "dur": 1938.420, + "args": { + "External id": 1430096,"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": 2338706, "tid": 2379422, + "ts": 6413850810250.440, "dur": 0.639, + "args": { + "External id": 1430097,"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": 2338706, "tid": 2379422, + "ts": 6413850810252.707, "dur": 2.983, + "args": { + "External id": 1430098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810254.267, "dur": 1.287, + "args": { + "External id": 1430099,"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": 2338706, "tid": 2379422, + "ts": 6413850810261.157, "dur": 27.784, + "args": { + "External id": 1430100,"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": 2338706, "tid": 2379422, + "ts": 6413850810295.867, "dur": 47.091, + "args": { + "External id": 1430101,"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": 2338706, "tid": 2379422, + "ts": 6413850810300.808, "dur": 41.939, + "args": { + "External id": 1430102,"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": 2338706, "tid": 2379422, + "ts": 6413850810302.395, "dur": 39.953, + "args": { + "External id": 1430103,"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": 2338706, "tid": 2379422, + "ts": 6413850810520.798, "dur": 22.096, + "args": { + "External id": 1430104,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 87 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810561.355, "dur": 18.144, + "args": { + "External id": 1430105,"Record function id": 0, "Sequence number": 15348872, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810563.296, "dur": 13.361, + "args": { + "External id": 1430106,"Sequence number": 15348872, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 89 + } + }, + { + "ph": "f", "id": 11, "pid": 2338706, "tid": 2379422, "ts": 6413850810563.296, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850810569.679, "dur": 6.725, + "args": { + "External id": 1430107,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 90 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850810571.106, "dur": 5.151, + "args": { + "External id": 1430108,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 91 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810583.632, "dur": 90.720, + "args": { + "External id": 1430109,"Record function id": 0, "Sequence number": 15348871, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810584.802, "dur": 83.756, + "args": { + "External id": 1430110,"Sequence number": 15348871, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 93 + } + }, + { + "ph": "f", "id": 12, "pid": 2338706, "tid": 2379422, "ts": 6413850810584.802, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850810586.805, "dur": 81.372, + "args": { + "External id": 1430111,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 94 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850810592.737, "dur": 29.325, + "args": { + "External id": 1430112,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 95 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850810594.779, "dur": 3.958, + "args": { + "External id": 1430113,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 96 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810599.768, "dur": 21.941, + "args": { + "External id": 1430114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 97 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810601.570, "dur": 19.534, + "args": { + "External id": 1430115,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 98 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850810623.819, "dur": 4.375, + "args": { + "External id": 1430116,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 99 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850810626.338, "dur": 1.481, + "args": { + "External id": 1430117,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810632.649, "dur": 34.431, + "args": { + "External id": 1430118,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810679.422, "dur": 64.888, + "args": { + "External id": 1430119,"Record function id": 0, "Sequence number": 15348870, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810680.405, "dur": 60.539, + "args": { + "External id": 1430120,"Sequence number": 15348870, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 103 + } + }, + { + "ph": "f", "id": 13, "pid": 2338706, "tid": 2379422, "ts": 6413850810680.405, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850810685.235, "dur": 55.370, + "args": { + "External id": 1430121,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850810687.156, "dur": 17.895, + "args": { + "External id": 1430122,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850810688.347, "dur": 2.804, + "args": { + "External id": 1430123,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810692.056, "dur": 12.683, + "args": { + "External id": 1430124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810693.299, "dur": 11.000, + "args": { + "External id": 1430125,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850810709.144, "dur": 11.393, + "args": { + "External id": 1430126,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850810715.672, "dur": 4.278, + "args": { + "External id": 1430127,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810721.742, "dur": 18.079, + "args": { + "External id": 1430128,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810751.864, "dur": 150.881, + "args": { + "External id": 1430129,"Record function id": 0, "Sequence number": 15348869, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810752.912, "dur": 145.583, + "args": { + "External id": 1430130,"Sequence number": 15348869, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 113 + } + }, + { + "ph": "f", "id": 14, "pid": 2338706, "tid": 2379422, "ts": 6413850810752.912, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850810754.293, "dur": 143.710, + "args": { + "External id": 1430131,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850810755.385, "dur": 16.868, + "args": { + "External id": 1430132,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850810756.255, "dur": 2.218, + "args": { + "External id": 1430133,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810759.115, "dur": 12.809, + "args": { + "External id": 1430134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810760.084, "dur": 11.466, + "args": { + "External id": 1430135,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850810775.998, "dur": 5.319, + "args": { + "External id": 1430136,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850810780.359, "dur": 0.684, + "args": { + "External id": 1430137,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810781.929, "dur": 115.021, + "args": { + "External id": 1430138,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810908.095, "dur": 135.578, + "args": { + "External id": 1430139,"Record function id": 0, "Sequence number": 15348868, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850810909.551, "dur": 108.320, + "args": { + "External id": 1430140,"Sequence number": 15348868, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 123 + } + }, + { + "ph": "f", "id": 15, "pid": 2338706, "tid": 2379422, "ts": 6413850810909.551, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850810914.247, "dur": 103.263, + "args": { + "External id": 1430141,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850810915.269, "dur": 18.400, + "args": { + "External id": 1430142,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850810916.414, "dur": 2.673, + "args": { + "External id": 1430143,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810919.691, "dur": 13.686, + "args": { + "External id": 1430144,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810920.851, "dur": 11.963, + "args": { + "External id": 1430145,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850810934.798, "dur": 2.067, + "args": { + "External id": 1430146,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850810935.942, "dur": 0.638, + "args": { + "External id": 1430147,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850810940.455, "dur": 75.707, + "args": { + "External id": 1430148,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850811024.901, "dur": 16.782, + "args": { + "External id": 1430149,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850811051.663, "dur": 97.219, + "args": { + "External id": 1430150,"Record function id": 0, "Sequence number": 15348867, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850811102.905, "dur": 2.096, + "args": { + "External id": 1430151,"Sequence number": 15348867, "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": 2338706, "tid": 2379422, "ts": 6413850811102.905, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850811109.527, "dur": 35.534, + "args": { + "External id": 1430152,"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": 2338706, "tid": 2379422, + "ts": 6413850811112.083, "dur": 32.514, + "args": { + "External id": 1430153,"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": 2338706, "tid": 2379422, + "ts": 6413850811121.511, "dur": 0.911, + "args": { + "External id": 1430154,"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": 2338706, "tid": 2379422, + "ts": 6413850811156.790, "dur": 3383.234, + "args": { + "External id": 1430155,"Record function id": 0, "Sequence number": 15348865, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850811160.447, "dur": 3339.625, + "args": { + "External id": 1430156,"Sequence number": 15348865, "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": 2338706, "tid": 2379422, "ts": 6413850811160.447, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850811200.792, "dur": 3.833, + "args": { + "External id": 1430157,"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": 2338706, "tid": 2379422, + "ts": 6413850811207.747, "dur": 3036.253, + "args": { + "External id": 1430158,"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": 2338706, "tid": 2379422, + "ts": 6413850811209.700, "dur": 3033.847, + "args": { + "External id": 1430159,"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": 2338706, "tid": 2379422, + "ts": 6413850811215.746, "dur": 5.652, + "args": { + "External id": 1430160,"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": 2338706, "tid": 2379422, + "ts": 6413850811222.202, "dur": 3020.098, + "args": { + "External id": 1430161,"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": 2338706, "tid": 2379422, + "ts": 6413850814249.844, "dur": 0.482, + "args": { + "External id": 1430162,"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": 2338706, "tid": 2379422, + "ts": 6413850814252.162, "dur": 6.724, + "args": { + "External id": 1430163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814257.563, "dur": 1.134, + "args": { + "External id": 1430164,"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": 2338706, "tid": 2379422, + "ts": 6413850814265.332, "dur": 29.767, + "args": { + "External id": 1430165,"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": 2338706, "tid": 2379422, + "ts": 6413850814303.735, "dur": 47.112, + "args": { + "External id": 1430166,"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": 2338706, "tid": 2379422, + "ts": 6413850814305.281, "dur": 45.335, + "args": { + "External id": 1430167,"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": 2338706, "tid": 2379422, + "ts": 6413850814307.547, "dur": 42.636, + "args": { + "External id": 1430168,"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": 2338706, "tid": 2379422, + "ts": 6413850814512.246, "dur": 23.671, + "args": { + "External id": 1430169,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814552.168, "dur": 14.071, + "args": { + "External id": 1430170,"Record function id": 0, "Sequence number": 15348864, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814553.656, "dur": 10.132, + "args": { + "External id": 1430171,"Sequence number": 15348864, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 154 + } + }, + { + "ph": "f", "id": 18, "pid": 2338706, "tid": 2379422, "ts": 6413850814553.656, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850814557.351, "dur": 6.182, + "args": { + "External id": 1430172,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850814558.668, "dur": 4.676, + "args": { + "External id": 1430173,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814570.381, "dur": 86.491, + "args": { + "External id": 1430174,"Record function id": 0, "Sequence number": 15348863, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814571.244, "dur": 80.417, + "args": { + "External id": 1430175,"Sequence number": 15348863, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 158 + } + }, + { + "ph": "f", "id": 19, "pid": 2338706, "tid": 2379422, "ts": 6413850814571.244, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850814576.016, "dur": 75.164, + "args": { + "External id": 1430176,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850814579.426, "dur": 27.808, + "args": { + "External id": 1430177,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850814583.948, "dur": 4.075, + "args": { + "External id": 1430178,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814589.115, "dur": 17.813, + "args": { + "External id": 1430179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814590.814, "dur": 15.598, + "args": { + "External id": 1430180,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850814608.931, "dur": 6.814, + "args": { + "External id": 1430181,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850814613.845, "dur": 1.514, + "args": { + "External id": 1430182,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814617.408, "dur": 32.759, + "args": { + "External id": 1430183,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814661.948, "dur": 61.626, + "args": { + "External id": 1430184,"Record function id": 0, "Sequence number": 15348862, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814662.928, "dur": 57.491, + "args": { + "External id": 1430185,"Sequence number": 15348862, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 168 + } + }, + { + "ph": "f", "id": 20, "pid": 2338706, "tid": 2379422, "ts": 6413850814662.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850814665.160, "dur": 54.780, + "args": { + "External id": 1430186,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850814667.396, "dur": 21.684, + "args": { + "External id": 1430187,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850814668.138, "dur": 3.393, + "args": { + "External id": 1430188,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814672.379, "dur": 16.393, + "args": { + "External id": 1430189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814675.480, "dur": 12.831, + "args": { + "External id": 1430190,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850814690.621, "dur": 8.259, + "args": { + "External id": 1430191,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850814697.240, "dur": 1.093, + "args": { + "External id": 1430192,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814699.924, "dur": 19.276, + "args": { + "External id": 1430193,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814727.751, "dur": 133.163, + "args": { + "External id": 1430194,"Record function id": 0, "Sequence number": 15348861, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814729.035, "dur": 127.533, + "args": { + "External id": 1430195,"Sequence number": 15348861, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 178 + } + }, + { + "ph": "f", "id": 21, "pid": 2338706, "tid": 2379422, "ts": 6413850814729.035, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850814730.807, "dur": 125.216, + "args": { + "External id": 1430196,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850814731.979, "dur": 20.124, + "args": { + "External id": 1430197,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850814732.764, "dur": 2.270, + "args": { + "External id": 1430198,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814735.708, "dur": 16.062, + "args": { + "External id": 1430199,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814738.956, "dur": 12.322, + "args": { + "External id": 1430200,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850814755.874, "dur": 5.254, + "args": { + "External id": 1430201,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850814760.374, "dur": 0.521, + "args": { + "External id": 1430202,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814762.132, "dur": 92.987, + "args": { + "External id": 1430203,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814866.774, "dur": 147.302, + "args": { + "External id": 1430204,"Record function id": 0, "Sequence number": 15348860, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850814868.096, "dur": 101.060, + "args": { + "External id": 1430205,"Sequence number": 15348860, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 188 + } + }, + { + "ph": "f", "id": 22, "pid": 2338706, "tid": 2379422, "ts": 6413850814868.096, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850814872.567, "dur": 96.277, + "args": { + "External id": 1430206,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850814873.882, "dur": 22.382, + "args": { + "External id": 1430207,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850814874.738, "dur": 4.564, + "args": { + "External id": 1430208,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814880.170, "dur": 15.772, + "args": { + "External id": 1430209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814881.269, "dur": 14.180, + "args": { + "External id": 1430210,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850814897.368, "dur": 5.179, + "args": { + "External id": 1430211,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850814901.385, "dur": 0.842, + "args": { + "External id": 1430212,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814905.957, "dur": 61.951, + "args": { + "External id": 1430213,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850814973.589, "dur": 37.748, + "args": { + "External id": 1430214,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850815024.337, "dur": 77.440, + "args": { + "External id": 1430215,"Record function id": 0, "Sequence number": 15348859, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850815026.068, "dur": 1.224, + "args": { + "External id": 1430216,"Sequence number": 15348859, "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": 2338706, "tid": 2379422, "ts": 6413850815026.068, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850815029.912, "dur": 64.236, + "args": { + "External id": 1430217,"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": 2338706, "tid": 2379422, + "ts": 6413850815032.211, "dur": 60.899, + "args": { + "External id": 1430218,"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": 2338706, "tid": 2379422, + "ts": 6413850815038.029, "dur": 0.815, + "args": { + "External id": 1430219,"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": 2338706, "tid": 2379422, + "ts": 6413850815109.893, "dur": 3400.886, + "args": { + "External id": 1430220,"Record function id": 0, "Sequence number": 15348858, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850815123.974, "dur": 3350.453, + "args": { + "External id": 1430221,"Sequence number": 15348858, "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": 2338706, "tid": 2379422, "ts": 6413850815123.974, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850815158.484, "dur": 3.021, + "args": { + "External id": 1430222,"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": 2338706, "tid": 2379422, + "ts": 6413850815164.345, "dur": 3077.514, + "args": { + "External id": 1430223,"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": 2338706, "tid": 2379422, + "ts": 6413850815166.029, "dur": 3075.332, + "args": { + "External id": 1430224,"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": 2338706, "tid": 2379422, + "ts": 6413850815172.144, "dur": 4.380, + "args": { + "External id": 1430225,"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": 2338706, "tid": 2379422, + "ts": 6413850815177.377, "dur": 3062.602, + "args": { + "External id": 1430226,"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": 2338706, "tid": 2379422, + "ts": 6413850818245.931, "dur": 0.381, + "args": { + "External id": 1430227,"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": 2338706, "tid": 2379422, + "ts": 6413850818247.929, "dur": 5.390, + "args": { + "External id": 1430228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818252.097, "dur": 1.039, + "args": { + "External id": 1430229,"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": 2338706, "tid": 2379422, + "ts": 6413850818258.129, "dur": 26.999, + "args": { + "External id": 1430230,"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": 2338706, "tid": 2379422, + "ts": 6413850818290.650, "dur": 46.118, + "args": { + "External id": 1430231,"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": 2338706, "tid": 2379422, + "ts": 6413850818291.847, "dur": 44.671, + "args": { + "External id": 1430232,"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": 2338706, "tid": 2379422, + "ts": 6413850818293.258, "dur": 42.860, + "args": { + "External id": 1430233,"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": 2338706, "tid": 2379422, + "ts": 6413850818487.574, "dur": 18.448, + "args": { + "External id": 1430234,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850818528.155, "dur": 14.509, + "args": { + "External id": 1430235,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850818530.848, "dur": 10.056, + "args": { + "External id": 1430236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850818534.616, "dur": 5.091, + "args": { + "External id": 1430237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850818535.894, "dur": 3.705, + "args": { + "External id": 1430238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818547.321, "dur": 15.659, + "args": { + "External id": 1430239,"Record function id": 0, "Sequence number": 15348857, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818548.453, "dur": 11.951, + "args": { + "External id": 1430240,"Sequence number": 15348857, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 223 + } + }, + { + "ph": "f", "id": 25, "pid": 2338706, "tid": 2379422, "ts": 6413850818548.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850818552.059, "dur": 8.058, + "args": { + "External id": 1430241,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850818556.254, "dur": 3.688, + "args": { + "External id": 1430242,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818567.079, "dur": 80.594, + "args": { + "External id": 1430243,"Record function id": 0, "Sequence number": 15348856, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818568.083, "dur": 74.862, + "args": { + "External id": 1430244,"Sequence number": 15348856, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 227 + } + }, + { + "ph": "f", "id": 26, "pid": 2338706, "tid": 2379422, "ts": 6413850818568.083, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850818570.315, "dur": 72.136, + "args": { + "External id": 1430245,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850818576.428, "dur": 27.896, + "args": { + "External id": 1430246,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850818578.503, "dur": 7.443, + "args": { + "External id": 1430247,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818586.795, "dur": 17.225, + "args": { + "External id": 1430248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818588.531, "dur": 14.948, + "args": { + "External id": 1430249,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850818606.032, "dur": 6.977, + "args": { + "External id": 1430250,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850818611.276, "dur": 1.370, + "args": { + "External id": 1430251,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818614.424, "dur": 27.214, + "args": { + "External id": 1430252,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818652.808, "dur": 62.758, + "args": { + "External id": 1430253,"Record function id": 0, "Sequence number": 15348855, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818654.038, "dur": 58.515, + "args": { + "External id": 1430254,"Sequence number": 15348855, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 237 + } + }, + { + "ph": "f", "id": 27, "pid": 2338706, "tid": 2379422, "ts": 6413850818654.038, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850818656.236, "dur": 55.973, + "args": { + "External id": 1430255,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850818658.596, "dur": 27.378, + "args": { + "External id": 1430256,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850818664.573, "dur": 3.296, + "args": { + "External id": 1430257,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818672.067, "dur": 13.613, + "args": { + "External id": 1430258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818673.409, "dur": 11.835, + "args": { + "External id": 1430259,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850818687.175, "dur": 5.151, + "args": { + "External id": 1430260,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850818690.724, "dur": 1.033, + "args": { + "External id": 1430261,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818693.158, "dur": 18.350, + "args": { + "External id": 1430262,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818719.836, "dur": 131.375, + "args": { + "External id": 1430263,"Record function id": 0, "Sequence number": 15348854, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818721.048, "dur": 126.377, + "args": { + "External id": 1430264,"Sequence number": 15348854, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 247 + } + }, + { + "ph": "f", "id": 28, "pid": 2338706, "tid": 2379422, "ts": 6413850818721.048, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850818722.904, "dur": 123.846, + "args": { + "External id": 1430265,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850818726.440, "dur": 20.201, + "args": { + "External id": 1430266,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850818727.303, "dur": 2.301, + "args": { + "External id": 1430267,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818730.245, "dur": 16.116, + "args": { + "External id": 1430268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818733.293, "dur": 12.676, + "args": { + "External id": 1430269,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850818747.779, "dur": 2.329, + "args": { + "External id": 1430270,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850818749.125, "dur": 0.777, + "args": { + "External id": 1430271,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818750.908, "dur": 94.976, + "args": { + "External id": 1430272,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818856.897, "dur": 169.027, + "args": { + "External id": 1430273,"Record function id": 0, "Sequence number": 15348853, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850818857.867, "dur": 137.171, + "args": { + "External id": 1430274,"Sequence number": 15348853, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 257 + } + }, + { + "ph": "f", "id": 29, "pid": 2338706, "tid": 2379422, "ts": 6413850818857.867, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850818859.287, "dur": 135.127, + "args": { + "External id": 1430275,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413850818860.473, "dur": 47.553, + "args": { + "External id": 1430276,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850818866.266, "dur": 2.571, + "args": { + "External id": 1430277,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818888.435, "dur": 19.279, + "args": { + "External id": 1430278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818893.424, "dur": 13.821, + "args": { + "External id": 1430279,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850818911.695, "dur": 2.773, + "args": { + "External id": 1430280,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850818913.558, "dur": 0.638, + "args": { + "External id": 1430281,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850818915.213, "dur": 77.675, + "args": { + "External id": 1430282,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850819003.825, "dur": 19.324, + "args": { + "External id": 1430283,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850819035.388, "dur": 441.966, + "args": { + "External id": 1430284,"Record function id": 0, "Sequence number": 15348852, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850819037.072, "dur": 428.457, + "args": { + "External id": 1430285,"Sequence number": 15348852, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 268 + } + }, + { + "ph": "f", "id": 30, "pid": 2338706, "tid": 2379422, "ts": 6413850819037.072, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413850819275.402, "dur": 53.875, + "args": { + "External id": 1430286,"kernel_hash": "cxv3u4whmia24aefmfuiol55m7osx2elddgy6rxbkbvmnigizet6", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "131072", "4096", "1", "993", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xv/cxv3u4whmia24aefmfuiol55m7osx2elddgy6rxbkbvmnigizet6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [4096], [131072, 4096], [131072, 4096], [132, 4096], [131072], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 2338706, "tid": 2379422, + "ts": 6413850819371.495, "dur": 30.184, + "args": { + "External id": 1430287,"kernel_hash": "chd4lphpu733jd27rokzqqzh23vkeai2aitqgvmlc7xjqod3vr6m", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/hd/chd4lphpu733jd27rokzqqzh23vkeai2aitqgvmlc7xjqod3vr6m.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 2338706, "tid": 2379422, + "ts": 6413850819420.550, "dur": 19.741, + "args": { + "External id": 1430288,"kernel_hash": "cginwarxhlqgizmvepo2jober6dgvr4lj6cd6nlltcu72kqzvxpx", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/gi/cginwarxhlqgizmvepo2jober6dgvr4lj6cd6nlltcu72kqzvxpx.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850819491.648, "dur": 18.566, + "args": { + "External id": 1430289,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850819494.043, "dur": 15.229, + "args": { + "External id": 1430290,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850819497.292, "dur": 10.992, + "args": { + "External id": 1430291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850819501.416, "dur": 6.722, + "args": { + "External id": 1430292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850819515.194, "dur": 41.497, + "args": { + "External id": 1430293,"Record function id": 0, "Sequence number": 15348851, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850819516.526, "dur": 31.737, + "args": { + "External id": 1430294,"Sequence number": 15348851, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 277 + } + }, + { + "ph": "f", "id": 31, "pid": 2338706, "tid": 2379422, "ts": 6413850819516.526, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850819519.003, "dur": 10.546, + "args": { + "External id": 1430295,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819525.619, "dur": 1.758, + "args": { + "External id": 1430296,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850819530.093, "dur": 9.017, + "args": { + "External id": 1430297,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819537.665, "dur": 0.572, + "args": { + "External id": 1430298,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850819539.546, "dur": 2.744, + "args": { + "External id": 1430299,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819540.636, "dur": 0.486, + "args": { + "External id": 1430300,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413850819542.868, "dur": 4.621, + "args": { + "External id": 1430301,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819546.155, "dur": 0.434, + "args": { + "External id": 1430302,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850819560.990, "dur": 5.834, + "args": { + "External id": 1430303,"Record function id": 0, "Sequence number": 15348850, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850819561.911, "dur": 1.139, + "args": { + "External id": 1430304,"Sequence number": 15348850, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 287 + } + }, + { + "ph": "f", "id": 32, "pid": 2338706, "tid": 2379422, "ts": 6413850819561.911, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850819571.826, "dur": 690.804, + "args": { + "External id": 1430305,"Record function id": 0, "Sequence number": 15348849, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850819573.050, "dur": 674.033, + "args": { + "External id": 1430306,"Sequence number": 15348849, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 289 + } + }, + { + "ph": "f", "id": 33, "pid": 2338706, "tid": 2379422, "ts": 6413850819573.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850819617.666, "dur": 14.986, + "args": { + "External id": 1430307,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850819626.542, "dur": 5.697, + "args": { + "External id": 1430308,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850819637.154, "dur": 9.937, + "args": { + "External id": 1430309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850819640.009, "dur": 5.631, + "args": { + "External id": 1430310,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819644.598, "dur": 0.779, + "args": { + "External id": 1430311,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413850819651.209, "dur": 154.487, + "args": { + "External id": 1430312,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850819652.143, "dur": 5.696, + "args": { + "External id": 1430313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850819652.724, "dur": 4.262, + "args": { + "External id": 1430314,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819656.352, "dur": 0.494, + "args": { + "External id": 1430315,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413850819659.448, "dur": 145.455, + "args": { + "External id": 1430316,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850819661.079, "dur": 142.692, + "args": { + "External id": 1430317,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850819815.179, "dur": 5.310, + "args": { + "External id": 1430318,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850819817.194, "dur": 3.120, + "args": { + "External id": 1430319,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850819858.843, "dur": 5.561, + "args": { + "External id": 1430320,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850819865.560, "dur": 1.922, + "args": { + "External id": 1430321,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850819871.377, "dur": 2.451, + "args": { + "External id": 1430322,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850819924.110, "dur": 2.523, + "args": { + "External id": 1430323,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850819924.863, "dur": 1.571, + "args": { + "External id": 1430324,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413850819955.098, "dur": 259.018, + "args": { + "External id": 1430325,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850819962.849, "dur": 9.925, + "args": { + "External id": 1430326,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850819969.014, "dur": 0.902, + "args": { + "External id": 1430327,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850819997.630, "dur": 9.684, + "args": { + "External id": 1430328,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820005.046, "dur": 1.064, + "args": { + "External id": 1430329,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850820009.802, "dur": 7.552, + "args": { + "External id": 1430330,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820014.104, "dur": 2.689, + "args": { + "External id": 1430331,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850820018.355, "dur": 4.879, + "args": { + "External id": 1430332,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820022.008, "dur": 0.687, + "args": { + "External id": 1430333,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850820030.588, "dur": 4.993, + "args": { + "External id": 1430334,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820034.647, "dur": 0.601, + "args": { + "External id": 1430335,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820036.363, "dur": 8.559, + "args": { + "External id": 1430336,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850820042.528, "dur": 2.189, + "args": { + "External id": 1430337,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850820045.774, "dur": 4.076, + "args": { + "External id": 1430338,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820049.064, "dur": 0.420, + "args": { + "External id": 1430339,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820050.440, "dur": 43.893, + "args": { + "External id": 1430340,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820051.410, "dur": 41.410, + "args": { + "External id": 1430341,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413850820097.888, "dur": 98.175, + "args": { + "External id": 1430342,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820198.623, "dur": 1.599, + "args": { + "External id": 1430343,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850820203.927, "dur": 5.209, + "args": { + "External id": 1430344,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820205.312, "dur": 3.099, + "args": { + "External id": 1430345,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820211.620, "dur": 1.042, + "args": { + "External id": 1430346,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850820279.524, "dur": 12.310, + "args": { + "External id": 1430347,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850820282.344, "dur": 8.608, + "args": { + "External id": 1430348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850820285.130, "dur": 4.763, + "args": { + "External id": 1430349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850820286.497, "dur": 3.072, + "args": { + "External id": 1430350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820296.810, "dur": 10.224, + "args": { + "External id": 1430351,"Record function id": 0, "Sequence number": 15348848, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820297.950, "dur": 6.375, + "args": { + "External id": 1430352,"Sequence number": 15348848, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 335 + } + }, + { + "ph": "f", "id": 34, "pid": 2338706, "tid": 2379422, "ts": 6413850820297.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820302.164, "dur": 1.878, + "args": { + "External id": 1430353,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820302.846, "dur": 1.028, + "args": { + "External id": 1430354,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820314.735, "dur": 149.482, + "args": { + "External id": 1430355,"Record function id": 0, "Sequence number": 15348847, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820315.698, "dur": 139.278, + "args": { + "External id": 1430356,"Sequence number": 15348847, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 339 + } + }, + { + "ph": "f", "id": 35, "pid": 2338706, "tid": 2379422, "ts": 6413850820315.698, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820320.371, "dur": 5.043, + "args": { + "External id": 1430357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820322.587, "dur": 2.213, + "args": { + "External id": 1430358,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820323.685, "dur": 0.872, + "args": { + "External id": 1430359,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850820327.250, "dur": 59.978, + "args": { + "External id": 1430360,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820388.971, "dur": 6.709, + "args": { + "External id": 1430361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820392.475, "dur": 2.488, + "args": { + "External id": 1430362,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820393.660, "dur": 1.094, + "args": { + "External id": 1430363,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820397.510, "dur": 5.940, + "args": { + "External id": 1430364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820398.467, "dur": 4.467, + "args": { + "External id": 1430365,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820402.063, "dur": 0.760, + "args": { + "External id": 1430366,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850820404.084, "dur": 50.104, + "args": { + "External id": 1430367,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820469.947, "dur": 12.279, + "args": { + "External id": 1430368,"Record function id": 0, "Sequence number": 15348846, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820471.115, "dur": 9.257, + "args": { + "External id": 1430369,"Sequence number": 15348846, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 352 + } + }, + { + "ph": "f", "id": 36, "pid": 2338706, "tid": 2379422, "ts": 6413850820471.115, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820475.515, "dur": 4.696, + "args": { + "External id": 1430370,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820476.315, "dur": 3.731, + "args": { + "External id": 1430371,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820486.685, "dur": 10.640, + "args": { + "External id": 1430372,"Record function id": 0, "Sequence number": 15348845, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820487.760, "dur": 7.136, + "args": { + "External id": 1430373,"Sequence number": 15348845, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 356 + } + }, + { + "ph": "f", "id": 37, "pid": 2338706, "tid": 2379422, "ts": 6413850820487.760, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820488.979, "dur": 5.692, + "args": { + "External id": 1430374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820489.684, "dur": 4.465, + "args": { + "External id": 1430375,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820493.471, "dur": 0.521, + "args": { + "External id": 1430376,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850820502.239, "dur": 8.820, + "args": { + "External id": 1430377,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850820504.092, "dur": 6.329, + "args": { + "External id": 1430378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850820505.166, "dur": 4.899, + "args": { + "External id": 1430379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850820508.636, "dur": 1.300, + "args": { + "External id": 1430380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820517.541, "dur": 6.923, + "args": { + "External id": 1430381,"Record function id": 0, "Sequence number": 15348844, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820518.663, "dur": 3.148, + "args": { + "External id": 1430382,"Sequence number": 15348844, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 365 + } + }, + { + "ph": "f", "id": 38, "pid": 2338706, "tid": 2379422, "ts": 6413850820518.663, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820520.176, "dur": 1.457, + "args": { + "External id": 1430383,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820520.678, "dur": 0.797, + "args": { + "External id": 1430384,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820528.231, "dur": 124.009, + "args": { + "External id": 1430385,"Record function id": 0, "Sequence number": 15348843, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820528.964, "dur": 114.866, + "args": { + "External id": 1430386,"Sequence number": 15348843, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 369 + } + }, + { + "ph": "f", "id": 39, "pid": 2338706, "tid": 2379422, "ts": 6413850820528.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820531.446, "dur": 4.816, + "args": { + "External id": 1430387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820532.091, "dur": 3.675, + "args": { + "External id": 1430388,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820535.192, "dur": 0.409, + "args": { + "External id": 1430389,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850820536.814, "dur": 48.763, + "args": { + "External id": 1430390,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820586.883, "dur": 6.283, + "args": { + "External id": 1430391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820587.591, "dur": 5.038, + "args": { + "External id": 1430392,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820591.477, "dur": 1.014, + "args": { + "External id": 1430393,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820594.410, "dur": 6.325, + "args": { + "External id": 1430394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820598.753, "dur": 1.506, + "args": { + "External id": 1430395,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820599.664, "dur": 0.487, + "args": { + "External id": 1430396,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850820601.507, "dur": 41.304, + "args": { + "External id": 1430397,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820657.752, "dur": 44.586, + "args": { + "External id": 1430398,"Record function id": 0, "Sequence number": 15348842, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820658.907, "dur": 7.059, + "args": { + "External id": 1430399,"Sequence number": 15348842, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 382 + } + }, + { + "ph": "f", "id": 40, "pid": 2338706, "tid": 2379422, "ts": 6413850820658.907, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820660.461, "dur": 5.334, + "args": { + "External id": 1430400,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820664.355, "dur": 1.305, + "args": { + "External id": 1430401,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850820669.935, "dur": 29.425, + "args": { + "External id": 1430402,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820707.327, "dur": 10.621, + "args": { + "External id": 1430403,"Record function id": 0, "Sequence number": 15348841, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850820710.514, "dur": 4.589, + "args": { + "External id": 1430404,"Sequence number": 15348841, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 387 + } + }, + { + "ph": "f", "id": 41, "pid": 2338706, "tid": 2379422, "ts": 6413850820710.514, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850820711.225, "dur": 3.616, + "args": { + "External id": 1430405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850820712.138, "dur": 2.155, + "args": { + "External id": 1430406,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850820713.520, "dur": 0.599, + "args": { + "External id": 1430407,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850820722.551, "dur": 5.899, + "args": { + "External id": 1430408,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850820723.874, "dur": 3.997, + "args": { + "External id": 1430409,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850820725.137, "dur": 2.365, + "args": { + "External id": 1430410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850820725.887, "dur": 1.507, + "args": { + "External id": 1430411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850820733.436, "dur": 579.544, + "args": { + "External id": 1430412,"Record function id": 0, "Sequence number": 15348840, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850820734.839, "dur": 561.805, + "args": { + "External id": 1430413,"Sequence number": 15348840, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 396 + } + }, + { + "ph": "f", "id": 42, "pid": 2338706, "tid": 2379422, "ts": 6413850820734.839, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413850820765.200, "dur": 39.599, + "args": { + "External id": 1430414,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850820766.946, "dur": 37.556, + "args": { + "External id": 1430415,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850820769.964, "dur": 6.870, + "args": { + "External id": 1430416,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850820772.700, "dur": 3.526, + "args": { + "External id": 1430417,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850820778.830, "dur": 25.069, + "args": { + "External id": 1430418,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820821.517, "dur": 2.712, + "args": { + "External id": 1430419,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820822.484, "dur": 1.616, + "args": { + "External id": 1430420,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850820828.595, "dur": 1.874, + "args": { + "External id": 1430421,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850820829.231, "dur": 1.096, + "args": { + "External id": 1430422,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850820850.222, "dur": 5.483, + "args": { + "External id": 1430423,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850820870.020, "dur": 2.804, + "args": { + "External id": 1430424,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821152.507, "dur": 5.493, + "args": { + "External id": 1430425,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850821163.720, "dur": 46.372, + "args": { + "External id": 1430426,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821180.663, "dur": 1.133, + "args": { + "External id": 1430427,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850821217.898, "dur": 37.547, + "args": { + "External id": 1430428,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850821219.970, "dur": 35.151, + "args": { + "External id": 1430429,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821227.418, "dur": 4.754, + "args": { + "External id": 1430430,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850821233.999, "dur": 20.375, + "args": { + "External id": 1430431,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850821261.259, "dur": 3.014, + "args": { + "External id": 1430432,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821262.567, "dur": 1.585, + "args": { + "External id": 1430433,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821273.197, "dur": 5.261, + "args": { + "External id": 1430434,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821276.687, "dur": 1.647, + "args": { + "External id": 1430435,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821280.923, "dur": 3.998, + "args": { + "External id": 1430436,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821284.041, "dur": 0.770, + "args": { + "External id": 1430437,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850821328.986, "dur": 10.067, + "args": { + "External id": 1430438,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850821331.118, "dur": 7.152, + "args": { + "External id": 1430439,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850821334.066, "dur": 3.104, + "args": { + "External id": 1430440,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850821335.140, "dur": 1.892, + "args": { + "External id": 1430441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821343.636, "dur": 14.669, + "args": { + "External id": 1430442,"Record function id": 0, "Sequence number": 15348839, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821344.578, "dur": 10.036, + "args": { + "External id": 1430443,"Sequence number": 15348839, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 426 + } + }, + { + "ph": "f", "id": 43, "pid": 2338706, "tid": 2379422, "ts": 6413850821344.578, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821349.241, "dur": 5.053, + "args": { + "External id": 1430444,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821352.771, "dur": 1.409, + "args": { + "External id": 1430445,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821362.308, "dur": 186.444, + "args": { + "External id": 1430446,"Record function id": 0, "Sequence number": 15348838, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821363.108, "dur": 180.344, + "args": { + "External id": 1430447,"Sequence number": 15348838, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 430 + } + }, + { + "ph": "f", "id": 44, "pid": 2338706, "tid": 2379422, "ts": 6413850821363.108, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850821366.812, "dur": 5.487, + "args": { + "External id": 1430448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850821368.707, "dur": 2.901, + "args": { + "External id": 1430449,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821370.496, "dur": 0.878, + "args": { + "External id": 1430450,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850821373.958, "dur": 88.863, + "args": { + "External id": 1430451,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850821464.201, "dur": 8.926, + "args": { + "External id": 1430452,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850821467.455, "dur": 4.881, + "args": { + "External id": 1430453,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821468.767, "dur": 3.354, + "args": { + "External id": 1430454,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850821475.134, "dur": 5.724, + "args": { + "External id": 1430455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850821475.951, "dur": 4.443, + "args": { + "External id": 1430456,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821479.811, "dur": 0.509, + "args": { + "External id": 1430457,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850821481.636, "dur": 61.004, + "args": { + "External id": 1430458,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821554.704, "dur": 9.741, + "args": { + "External id": 1430459,"Record function id": 0, "Sequence number": 15348837, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821555.916, "dur": 6.665, + "args": { + "External id": 1430460,"Sequence number": 15348837, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 443 + } + }, + { + "ph": "f", "id": 45, "pid": 2338706, "tid": 2379422, "ts": 6413850821555.916, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821559.908, "dur": 2.488, + "args": { + "External id": 1430461,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821560.709, "dur": 1.495, + "args": { + "External id": 1430462,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821568.424, "dur": 9.722, + "args": { + "External id": 1430463,"Record function id": 0, "Sequence number": 15348836, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821569.603, "dur": 6.379, + "args": { + "External id": 1430464,"Sequence number": 15348836, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 447 + } + }, + { + "ph": "f", "id": 46, "pid": 2338706, "tid": 2379422, "ts": 6413850821569.603, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850821570.541, "dur": 5.187, + "args": { + "External id": 1430465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850821571.289, "dur": 3.893, + "args": { + "External id": 1430466,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821574.471, "dur": 0.536, + "args": { + "External id": 1430467,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850821582.896, "dur": 8.360, + "args": { + "External id": 1430468,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850821584.187, "dur": 6.475, + "args": { + "External id": 1430469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850821585.391, "dur": 4.916, + "args": { + "External id": 1430470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850821588.795, "dur": 1.253, + "args": { + "External id": 1430471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821595.145, "dur": 7.155, + "args": { + "External id": 1430472,"Record function id": 0, "Sequence number": 15348835, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850821596.288, "dur": 3.556, + "args": { + "External id": 1430473,"Sequence number": 15348835, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 456 + } + }, + { + "ph": "f", "id": 47, "pid": 2338706, "tid": 2379422, "ts": 6413850821596.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821597.530, "dur": 2.145, + "args": { + "External id": 1430474,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821598.169, "dur": 1.393, + "args": { + "External id": 1430475,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850821610.790, "dur": 535.957, + "args": { + "External id": 1430476,"Record function id": 0, "Sequence number": 15348834, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850821612.202, "dur": 511.460, + "args": { + "External id": 1430477,"Sequence number": 15348834, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 460 + } + }, + { + "ph": "f", "id": 48, "pid": 2338706, "tid": 2379422, "ts": 6413850821612.202, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850821632.669, "dur": 16.892, + "args": { + "External id": 1430478,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821640.923, "dur": 8.144, + "args": { + "External id": 1430479,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850821652.033, "dur": 4.249, + "args": { + "External id": 1430480,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821653.170, "dur": 2.860, + "args": { + "External id": 1430481,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850821657.790, "dur": 6.159, + "args": { + "External id": 1430482,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821661.589, "dur": 2.133, + "args": { + "External id": 1430483,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850821716.097, "dur": 332.174, + "args": { + "External id": 1430484,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850821830.683, "dur": 5.605, + "args": { + "External id": 1430485,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850821838.286, "dur": 2.896, + "args": { + "External id": 1430486,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850821844.773, "dur": 2.013, + "args": { + "External id": 1430487,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850821848.050, "dur": 2.608, + "args": { + "External id": 1430488,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821909.627, "dur": 3.184, + "args": { + "External id": 1430489,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821910.659, "dur": 1.999, + "args": { + "External id": 1430490,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850821914.437, "dur": 33.395, + "args": { + "External id": 1430491,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821919.254, "dur": 5.457, + "args": { + "External id": 1430492,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850821951.856, "dur": 1.582, + "args": { + "External id": 1430493,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850821952.559, "dur": 0.773, + "args": { + "External id": 1430494,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850821957.364, "dur": 16.592, + "args": { + "External id": 1430495,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850821960.964, "dur": 0.458, + "args": { + "External id": 1430496,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850822106.368, "dur": 5.358, + "args": { + "External id": 1430497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850822116.258, "dur": 0.706, + "args": { + "External id": 1430498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850822119.390, "dur": 0.804, + "args": { + "External id": 1430499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850822161.797, "dur": 291.432, + "args": { + "External id": 1430500,"Record function id": 0, "Sequence number": 15348833, "Fwd thread id": 1, "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850822163.922, "dur": 281.248, + "args": { + "External id": 1430501,"Sequence number": 15348833, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 484 + } + }, + { + "ph": "f", "id": 49, "pid": 2338706, "tid": 2379422, "ts": 6413850822163.922, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850822191.221, "dur": 62.991, + "args": { + "External id": 1430502,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822195.007, "dur": 5.260, + "args": { + "External id": 1430503,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850822202.182, "dur": 51.261, + "args": { + "External id": 1430504,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850822266.993, "dur": 8.290, + "args": { + "External id": 1430505,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822271.995, "dur": 2.970, + "args": { + "External id": 1430506,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850822461.356, "dur": 203.544, + "args": { + "External id": 1430507,"Record function id": 0, "Sequence number": 15348832, "Fwd thread id": 1, "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850822463.363, "dur": 194.286, + "args": { + "External id": 1430508,"Sequence number": 15348832, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 491 + } + }, + { + "ph": "f", "id": 50, "pid": 2338706, "tid": 2379422, "ts": 6413850822463.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850822480.983, "dur": 54.794, + "args": { + "External id": 1430509,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822483.895, "dur": 3.175, + "args": { + "External id": 1430510,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850822488.243, "dur": 46.946, + "args": { + "External id": 1430511,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850822544.349, "dur": 9.508, + "args": { + "External id": 1430512,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822550.200, "dur": 3.332, + "args": { + "External id": 1430513,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822672.508, "dur": 17.422, + "args": { + "External id": 1430514,"Record function id": 0, "Sequence number": 15348831, "Fwd thread id": 1, "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822674.124, "dur": 12.132, + "args": { + "External id": 1430515,"Sequence number": 15348831, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 498 + } + }, + { + "ph": "f", "id": 51, "pid": 2338706, "tid": 2379422, "ts": 6413850822674.124, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850822676.621, "dur": 9.271, + "args": { + "External id": 1430516,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850822678.229, "dur": 7.439, + "args": { + "External id": 1430517,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822693.848, "dur": 12.954, + "args": { + "External id": 1430518,"Record function id": 0, "Sequence number": 15348830, "Fwd thread id": 1, "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822695.333, "dur": 8.919, + "args": { + "External id": 1430519,"Sequence number": 15348830, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 502 + } + }, + { + "ph": "f", "id": 52, "pid": 2338706, "tid": 2379422, "ts": 6413850822695.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850822696.594, "dur": 7.474, + "args": { + "External id": 1430520,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850822702.922, "dur": 1.023, + "args": { + "External id": 1430521,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822710.752, "dur": 5.956, + "args": { + "External id": 1430522,"Record function id": 0, "Sequence number": 15348829, "Fwd thread id": 1, "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822711.658, "dur": 3.017, + "args": { + "External id": 1430523,"Sequence number": 15348829, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 506 + } + }, + { + "ph": "f", "id": 53, "pid": 2338706, "tid": 2379422, "ts": 6413850822711.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850822712.625, "dur": 1.870, + "args": { + "External id": 1430524,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850822713.310, "dur": 1.076, + "args": { + "External id": 1430525,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822720.411, "dur": 109.688, + "args": { + "External id": 1430526,"Record function id": 0, "Sequence number": 15348828, "Fwd thread id": 1, "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822721.483, "dur": 105.322, + "args": { + "External id": 1430527,"Sequence number": 15348828, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 510 + } + }, + { + "ph": "f", "id": 54, "pid": 2338706, "tid": 2379422, "ts": 6413850822721.483, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850822725.405, "dur": 101.197, + "args": { + "External id": 1430528,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850822823.609, "dur": 2.727, + "args": { + "External id": 1430529,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822834.209, "dur": 257.809, + "args": { + "External id": 1430530,"Record function id": 0, "Sequence number": 15348827, "Fwd thread id": 1, "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850822838.025, "dur": 206.670, + "args": { + "External id": 1430531,"Sequence number": 15348827, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 514 + } + }, + { + "ph": "f", "id": 55, "pid": 2338706, "tid": 2379422, "ts": 6413850822838.025, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850822842.036, "dur": 7.569, + "args": { + "External id": 1430532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850822844.305, "dur": 4.535, + "args": { + "External id": 1430533,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822846.606, "dur": 1.882, + "args": { + "External id": 1430534,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850822851.485, "dur": 90.063, + "args": { + "External id": 1430535,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850822943.154, "dur": 9.381, + "args": { + "External id": 1430536,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850822944.044, "dur": 7.677, + "args": { + "External id": 1430537,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822948.274, "dur": 3.215, + "args": { + "External id": 1430538,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850822954.783, "dur": 6.312, + "args": { + "External id": 1430539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850822956.019, "dur": 4.523, + "args": { + "External id": 1430540,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850822959.934, "dur": 0.528, + "args": { + "External id": 1430541,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850822961.944, "dur": 80.953, + "args": { + "External id": 1430542,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823105.260, "dur": 12.569, + "args": { + "External id": 1430543,"Record function id": 0, "Sequence number": 15348826, "Fwd thread id": 1, "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823107.094, "dur": 8.389, + "args": { + "External id": 1430544,"Sequence number": 15348826, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 527 + } + }, + { + "ph": "f", "id": 56, "pid": 2338706, "tid": 2379422, "ts": 6413850823107.094, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823111.901, "dur": 3.362, + "args": { + "External id": 1430545,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823112.679, "dur": 2.467, + "args": { + "External id": 1430546,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823122.038, "dur": 11.682, + "args": { + "External id": 1430547,"Record function id": 0, "Sequence number": 15348825, "Fwd thread id": 1, "Ev Idx": 530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823122.966, "dur": 7.519, + "args": { + "External id": 1430548,"Sequence number": 15348825, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 531 + } + }, + { + "ph": "f", "id": 57, "pid": 2338706, "tid": 2379422, "ts": 6413850823122.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823123.837, "dur": 6.376, + "args": { + "External id": 1430549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823124.806, "dur": 4.837, + "args": { + "External id": 1430550,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823128.802, "dur": 0.687, + "args": { + "External id": 1430551,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850823140.548, "dur": 13.794, + "args": { + "External id": 1430552,"Record function id": 0, "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850823142.203, "dur": 11.221, + "args": { + "External id": 1430553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850823145.345, "dur": 7.607, + "args": { + "External id": 1430554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850823149.379, "dur": 3.427, + "args": { + "External id": 1430555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823161.359, "dur": 5.980, + "args": { + "External id": 1430556,"Record function id": 0, "Sequence number": 15348824, "Fwd thread id": 1, "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823162.383, "dur": 2.858, + "args": { + "External id": 1430557,"Sequence number": 15348824, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 540 + } + }, + { + "ph": "f", "id": 58, "pid": 2338706, "tid": 2379422, "ts": 6413850823162.383, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823163.456, "dur": 1.618, + "args": { + "External id": 1430558,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823163.959, "dur": 0.943, + "args": { + "External id": 1430559,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823171.183, "dur": 124.958, + "args": { + "External id": 1430560,"Record function id": 0, "Sequence number": 15348823, "Fwd thread id": 1, "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823172.287, "dur": 115.043, + "args": { + "External id": 1430561,"Sequence number": 15348823, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 544 + } + }, + { + "ph": "f", "id": 59, "pid": 2338706, "tid": 2379422, "ts": 6413850823172.287, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823175.173, "dur": 5.676, + "args": { + "External id": 1430562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823178.970, "dur": 1.375, + "args": { + "External id": 1430563,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823179.716, "dur": 0.500, + "args": { + "External id": 1430564,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850823181.786, "dur": 41.625, + "args": { + "External id": 1430565,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823224.685, "dur": 6.391, + "args": { + "External id": 1430566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823225.289, "dur": 5.140, + "args": { + "External id": 1430567,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823229.358, "dur": 0.924, + "args": { + "External id": 1430568,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823235.063, "dur": 5.520, + "args": { + "External id": 1430569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823235.783, "dur": 4.321, + "args": { + "External id": 1430570,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823236.539, "dur": 3.444, + "args": { + "External id": 1430571,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850823241.187, "dur": 45.235, + "args": { + "External id": 1430572,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823301.438, "dur": 44.096, + "args": { + "External id": 1430573,"Record function id": 0, "Sequence number": 15348822, "Fwd thread id": 1, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823302.365, "dur": 6.392, + "args": { + "External id": 1430574,"Sequence number": 15348822, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 557 + } + }, + { + "ph": "f", "id": 60, "pid": 2338706, "tid": 2379422, "ts": 6413850823302.365, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823303.949, "dur": 4.635, + "args": { + "External id": 1430575,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823307.234, "dur": 1.171, + "args": { + "External id": 1430576,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850823312.506, "dur": 29.788, + "args": { + "External id": 1430577,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823352.983, "dur": 7.328, + "args": { + "External id": 1430578,"Record function id": 0, "Sequence number": 15348821, "Fwd thread id": 1, "Ev Idx": 561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823354.149, "dur": 4.215, + "args": { + "External id": 1430579,"Sequence number": 15348821, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 562 + } + }, + { + "ph": "f", "id": 61, "pid": 2338706, "tid": 2379422, "ts": 6413850823354.149, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823354.901, "dur": 3.227, + "args": { + "External id": 1430580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823355.679, "dur": 1.915, + "args": { + "External id": 1430581,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823356.755, "dur": 0.709, + "args": { + "External id": 1430582,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850823364.856, "dur": 5.245, + "args": { + "External id": 1430583,"Record function id": 0, "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850823366.130, "dur": 3.361, + "args": { + "External id": 1430584,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850823367.163, "dur": 1.961, + "args": { + "External id": 1430585,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850823367.831, "dur": 1.180, + "args": { + "External id": 1430586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823373.680, "dur": 13.176, + "args": { + "External id": 1430587,"Record function id": 0, "Sequence number": 15348820, "Fwd thread id": 1, "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823375.044, "dur": 7.994, + "args": { + "External id": 1430588,"Sequence number": 15348820, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 571 + } + }, + { + "ph": "f", "id": 62, "pid": 2338706, "tid": 2379422, "ts": 6413850823375.044, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823381.155, "dur": 1.715, + "args": { + "External id": 1430589,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823381.698, "dur": 1.000, + "args": { + "External id": 1430590,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823390.564, "dur": 124.308, + "args": { + "External id": 1430591,"Record function id": 0, "Sequence number": 15348819, "Fwd thread id": 1, "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823391.578, "dur": 113.434, + "args": { + "External id": 1430592,"Sequence number": 15348819, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 575 + } + }, + { + "ph": "f", "id": 63, "pid": 2338706, "tid": 2379422, "ts": 6413850823391.578, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823394.238, "dur": 5.148, + "args": { + "External id": 1430593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823394.710, "dur": 4.161, + "args": { + "External id": 1430594,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823398.255, "dur": 0.488, + "args": { + "External id": 1430595,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850823403.476, "dur": 45.762, + "args": { + "External id": 1430596,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823450.438, "dur": 5.558, + "args": { + "External id": 1430597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823451.066, "dur": 4.253, + "args": { + "External id": 1430598,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823452.033, "dur": 3.130, + "args": { + "External id": 1430599,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823457.151, "dur": 8.000, + "args": { + "External id": 1430600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823457.833, "dur": 6.711, + "args": { + "External id": 1430601,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823463.672, "dur": 0.779, + "args": { + "External id": 1430602,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850823465.705, "dur": 38.482, + "args": { + "External id": 1430603,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823520.048, "dur": 29.264, + "args": { + "External id": 1430604,"Record function id": 0, "Sequence number": 15348818, "Fwd thread id": 1, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823521.239, "dur": 3.749, + "args": { + "External id": 1430605,"Sequence number": 15348818, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 588 + } + }, + { + "ph": "f", "id": 64, "pid": 2338706, "tid": 2379422, "ts": 6413850823521.239, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823522.783, "dur": 2.036, + "args": { + "External id": 1430606,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823523.445, "dur": 1.193, + "args": { + "External id": 1430607,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850823527.910, "dur": 18.911, + "args": { + "External id": 1430608,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823553.989, "dur": 14.117, + "args": { + "External id": 1430609,"Record function id": 0, "Sequence number": 15348817, "Fwd thread id": 1, "Ev Idx": 592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850823555.003, "dur": 10.496, + "args": { + "External id": 1430610,"Sequence number": 15348817, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 593 + } + }, + { + "ph": "f", "id": 65, "pid": 2338706, "tid": 2379422, "ts": 6413850823555.003, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850823556.023, "dur": 9.266, + "args": { + "External id": 1430611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850823559.755, "dur": 4.922, + "args": { + "External id": 1430612,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823563.954, "dur": 0.578, + "args": { + "External id": 1430613,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850823572.659, "dur": 5.841, + "args": { + "External id": 1430614,"Record function id": 0, "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850823574.349, "dur": 3.610, + "args": { + "External id": 1430615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850823575.401, "dur": 2.223, + "args": { + "External id": 1430616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850823576.125, "dur": 1.368, + "args": { + "External id": 1430617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850823583.677, "dur": 468.462, + "args": { + "External id": 1430618,"Record function id": 0, "Sequence number": 15348816, "Fwd thread id": 1, "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850823584.934, "dur": 419.609, + "args": { + "External id": 1430619,"Sequence number": 15348816, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 602 + } + }, + { + "ph": "f", "id": 66, "pid": 2338706, "tid": 2379422, "ts": 6413850823584.934, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823629.661, "dur": 2.360, + "args": { + "External id": 1430620,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823630.533, "dur": 1.370, + "args": { + "External id": 1430621,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850823652.373, "dur": 8.011, + "args": { + "External id": 1430622,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850823672.144, "dur": 2.363, + "args": { + "External id": 1430623,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823868.897, "dur": 2.335, + "args": { + "External id": 1430624,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850823875.706, "dur": 35.723, + "args": { + "External id": 1430625,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823885.362, "dur": 0.959, + "args": { + "External id": 1430626,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850823918.154, "dur": 34.734, + "args": { + "External id": 1430627,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850823920.324, "dur": 32.309, + "args": { + "External id": 1430628,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850823927.702, "dur": 4.334, + "args": { + "External id": 1430629,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850823934.222, "dur": 17.788, + "args": { + "External id": 1430630,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850823960.672, "dur": 2.700, + "args": { + "External id": 1430631,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823962.119, "dur": 1.103, + "args": { + "External id": 1430632,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850823970.372, "dur": 2.440, + "args": { + "External id": 1430633,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850823971.259, "dur": 1.403, + "args": { + "External id": 1430634,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850824020.850, "dur": 23.628, + "args": { + "External id": 1430635,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850824106.806, "dur": 15.665, + "args": { + "External id": 1430636,"Record function id": 0, "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850824112.241, "dur": 9.014, + "args": { + "External id": 1430637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850824115.223, "dur": 4.294, + "args": { + "External id": 1430638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850824116.462, "dur": 2.769, + "args": { + "External id": 1430639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824129.651, "dur": 7.909, + "args": { + "External id": 1430640,"Record function id": 0, "Sequence number": 15348815, "Fwd thread id": 1, "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824131.550, "dur": 1.837, + "args": { + "External id": 1430641,"Sequence number": 15348815, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 624 + } + }, + { + "ph": "f", "id": 67, "pid": 2338706, "tid": 2379422, "ts": 6413850824131.550, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850824141.958, "dur": 493.639, + "args": { + "External id": 1430642,"Record function id": 0, "Sequence number": 15348814, "Fwd thread id": 1, "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850824143.199, "dur": 479.783, + "args": { + "External id": 1430643,"Sequence number": 15348814, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 626 + } + }, + { + "ph": "f", "id": 68, "pid": 2338706, "tid": 2379422, "ts": 6413850824143.199, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824184.200, "dur": 10.051, + "args": { + "External id": 1430644,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850824189.470, "dur": 4.363, + "args": { + "External id": 1430645,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824198.099, "dur": 11.516, + "args": { + "External id": 1430646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824199.770, "dur": 9.090, + "args": { + "External id": 1430647,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824204.874, "dur": 3.801, + "args": { + "External id": 1430648,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413850824216.125, "dur": 105.320, + "args": { + "External id": 1430649,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824217.205, "dur": 2.861, + "args": { + "External id": 1430650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824217.896, "dur": 1.657, + "args": { + "External id": 1430651,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824218.768, "dur": 0.687, + "args": { + "External id": 1430652,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413850824221.670, "dur": 99.275, + "args": { + "External id": 1430653,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850824223.430, "dur": 96.294, + "args": { + "External id": 1430654,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850824326.231, "dur": 6.230, + "args": { + "External id": 1430655,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824330.586, "dur": 1.720, + "args": { + "External id": 1430656,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850824370.830, "dur": 6.370, + "args": { + "External id": 1430657,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850824381.533, "dur": 2.047, + "args": { + "External id": 1430658,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850824384.528, "dur": 1.867, + "args": { + "External id": 1430659,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824423.760, "dur": 2.624, + "args": { + "External id": 1430660,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824424.663, "dur": 1.532, + "args": { + "External id": 1430661,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413850824454.753, "dur": 145.394, + "args": { + "External id": 1430662,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850824460.691, "dur": 12.520, + "args": { + "External id": 1430663,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824466.393, "dur": 5.837, + "args": { + "External id": 1430664,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850824474.731, "dur": 7.236, + "args": { + "External id": 1430665,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824480.595, "dur": 0.500, + "args": { + "External id": 1430666,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850824483.561, "dur": 1.912, + "args": { + "External id": 1430667,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824484.296, "dur": 0.724, + "args": { + "External id": 1430668,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850824488.529, "dur": 2.461, + "args": { + "External id": 1430669,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824489.595, "dur": 0.489, + "args": { + "External id": 1430670,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850824497.599, "dur": 1.895, + "args": { + "External id": 1430671,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824498.576, "dur": 0.557, + "args": { + "External id": 1430672,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824502.734, "dur": 8.341, + "args": { + "External id": 1430673,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850824508.409, "dur": 2.451, + "args": { + "External id": 1430674,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850824511.976, "dur": 3.825, + "args": { + "External id": 1430675,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824515.098, "dur": 0.376, + "args": { + "External id": 1430676,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824516.580, "dur": 3.577, + "args": { + "External id": 1430677,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824517.320, "dur": 2.715, + "args": { + "External id": 1430678,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413850824521.528, "dur": 62.446, + "args": { + "External id": 1430679,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824588.788, "dur": 1.292, + "args": { + "External id": 1430680,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850824590.864, "dur": 4.647, + "args": { + "External id": 1430681,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824594.104, "dur": 0.761, + "args": { + "External id": 1430682,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824597.989, "dur": 0.982, + "args": { + "External id": 1430683,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850824645.550, "dur": 9.433, + "args": { + "External id": 1430684,"Record function id": 0, "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850824647.969, "dur": 6.320, + "args": { + "External id": 1430685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850824649.857, "dur": 3.448, + "args": { + "External id": 1430686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850824651.110, "dur": 2.037, + "args": { + "External id": 1430687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824659.439, "dur": 8.408, + "args": { + "External id": 1430688,"Record function id": 0, "Sequence number": 15348813, "Fwd thread id": 1, "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824660.472, "dur": 4.193, + "args": { + "External id": 1430689,"Sequence number": 15348813, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 672 + } + }, + { + "ph": "f", "id": 69, "pid": 2338706, "tid": 2379422, "ts": 6413850824660.472, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824662.622, "dur": 1.776, + "args": { + "External id": 1430690,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824663.339, "dur": 0.884, + "args": { + "External id": 1430691,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824671.984, "dur": 149.538, + "args": { + "External id": 1430692,"Record function id": 0, "Sequence number": 15348812, "Fwd thread id": 1, "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824675.556, "dur": 138.349, + "args": { + "External id": 1430693,"Sequence number": 15348812, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 676 + } + }, + { + "ph": "f", "id": 70, "pid": 2338706, "tid": 2379422, "ts": 6413850824675.556, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824679.061, "dur": 4.696, + "args": { + "External id": 1430694,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824680.570, "dur": 2.646, + "args": { + "External id": 1430695,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824681.863, "dur": 1.164, + "args": { + "External id": 1430696,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850824684.771, "dur": 45.731, + "args": { + "External id": 1430697,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824732.150, "dur": 9.093, + "args": { + "External id": 1430698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824733.420, "dur": 6.977, + "args": { + "External id": 1430699,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824739.044, "dur": 1.183, + "args": { + "External id": 1430700,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824742.679, "dur": 27.614, + "args": { + "External id": 1430701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824764.565, "dur": 5.100, + "args": { + "External id": 1430702,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824765.843, "dur": 3.652, + "args": { + "External id": 1430703,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850824770.791, "dur": 41.879, + "args": { + "External id": 1430704,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824827.516, "dur": 11.600, + "args": { + "External id": 1430705,"Record function id": 0, "Sequence number": 15348811, "Fwd thread id": 1, "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824828.678, "dur": 8.899, + "args": { + "External id": 1430706,"Sequence number": 15348811, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 689 + } + }, + { + "ph": "f", "id": 71, "pid": 2338706, "tid": 2379422, "ts": 6413850824828.678, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824832.473, "dur": 4.913, + "args": { + "External id": 1430707,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824835.786, "dur": 1.423, + "args": { + "External id": 1430708,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824843.342, "dur": 6.563, + "args": { + "External id": 1430709,"Record function id": 0, "Sequence number": 15348810, "Fwd thread id": 1, "Ev Idx": 692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824844.218, "dur": 3.827, + "args": { + "External id": 1430710,"Sequence number": 15348810, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 693 + } + }, + { + "ph": "f", "id": 72, "pid": 2338706, "tid": 2379422, "ts": 6413850824844.218, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824844.982, "dur": 2.803, + "args": { + "External id": 1430711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824845.737, "dur": 1.541, + "args": { + "External id": 1430712,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824846.580, "dur": 0.533, + "args": { + "External id": 1430713,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850824854.529, "dur": 8.703, + "args": { + "External id": 1430714,"Record function id": 0, "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850824855.930, "dur": 6.714, + "args": { + "External id": 1430715,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850824857.074, "dur": 5.276, + "args": { + "External id": 1430716,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850824860.638, "dur": 1.539, + "args": { + "External id": 1430717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824866.831, "dur": 8.277, + "args": { + "External id": 1430718,"Record function id": 0, "Sequence number": 15348809, "Fwd thread id": 1, "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824867.856, "dur": 4.844, + "args": { + "External id": 1430719,"Sequence number": 15348809, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 702 + } + }, + { + "ph": "f", "id": 73, "pid": 2338706, "tid": 2379422, "ts": 6413850824867.856, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850824868.723, "dur": 3.811, + "args": { + "External id": 1430720,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850824871.530, "dur": 0.782, + "args": { + "External id": 1430721,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824878.742, "dur": 135.404, + "args": { + "External id": 1430722,"Record function id": 0, "Sequence number": 15348808, "Fwd thread id": 1, "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850824879.621, "dur": 124.200, + "args": { + "External id": 1430723,"Sequence number": 15348808, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 706 + } + }, + { + "ph": "f", "id": 74, "pid": 2338706, "tid": 2379422, "ts": 6413850824879.621, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824882.500, "dur": 5.386, + "args": { + "External id": 1430724,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824883.245, "dur": 4.155, + "args": { + "External id": 1430725,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824886.511, "dur": 0.759, + "args": { + "External id": 1430726,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850824888.423, "dur": 37.114, + "args": { + "External id": 1430727,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824926.869, "dur": 5.932, + "args": { + "External id": 1430728,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824927.637, "dur": 4.579, + "args": { + "External id": 1430729,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824928.691, "dur": 3.392, + "args": { + "External id": 1430730,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850824933.894, "dur": 7.664, + "args": { + "External id": 1430731,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850824936.580, "dur": 4.426, + "args": { + "External id": 1430732,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850824940.125, "dur": 0.794, + "args": { + "External id": 1430733,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850824942.177, "dur": 60.048, + "args": { + "External id": 1430734,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825022.683, "dur": 74.841, + "args": { + "External id": 1430735,"Record function id": 0, "Sequence number": 15348807, "Fwd thread id": 1, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825024.071, "dur": 5.387, + "args": { + "External id": 1430736,"Sequence number": 15348807, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 719 + } + }, + { + "ph": "f", "id": 75, "pid": 2338706, "tid": 2379422, "ts": 6413850825024.071, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825026.458, "dur": 2.813, + "args": { + "External id": 1430737,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825027.304, "dur": 1.829, + "args": { + "External id": 1430738,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850825032.592, "dur": 59.654, + "args": { + "External id": 1430739,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825104.825, "dur": 13.368, + "args": { + "External id": 1430740,"Record function id": 0, "Sequence number": 15348806, "Fwd thread id": 1, "Ev Idx": 723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825106.460, "dur": 8.644, + "args": { + "External id": 1430741,"Sequence number": 15348806, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 724 + } + }, + { + "ph": "f", "id": 76, "pid": 2338706, "tid": 2379422, "ts": 6413850825106.460, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850825110.200, "dur": 4.638, + "args": { + "External id": 1430742,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850825111.480, "dur": 2.541, + "args": { + "External id": 1430743,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825113.125, "dur": 0.777, + "args": { + "External id": 1430744,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850825125.972, "dur": 6.898, + "args": { + "External id": 1430745,"Record function id": 0, "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850825127.443, "dur": 4.813, + "args": { + "External id": 1430746,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850825129.278, "dur": 2.592, + "args": { + "External id": 1430747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850825129.953, "dur": 1.793, + "args": { + "External id": 1430748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850825139.980, "dur": 491.165, + "args": { + "External id": 1430749,"Record function id": 0, "Sequence number": 15348805, "Fwd thread id": 1, "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850825141.366, "dur": 452.387, + "args": { + "External id": 1430750,"Sequence number": 15348805, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 733 + } + }, + { + "ph": "f", "id": 77, "pid": 2338706, "tid": 2379422, "ts": 6413850825141.366, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413850825171.768, "dur": 42.341, + "args": { + "External id": 1430751,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850825173.660, "dur": 40.207, + "args": { + "External id": 1430752,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850825176.980, "dur": 7.460, + "args": { + "External id": 1430753,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850825179.898, "dur": 3.878, + "args": { + "External id": 1430754,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850825185.951, "dur": 27.224, + "args": { + "External id": 1430755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825229.735, "dur": 7.835, + "args": { + "External id": 1430756,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825232.927, "dur": 4.524, + "args": { + "External id": 1430757,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825242.243, "dur": 1.865, + "args": { + "External id": 1430758,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825242.879, "dur": 1.102, + "args": { + "External id": 1430759,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850825261.496, "dur": 3.229, + "args": { + "External id": 1430760,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850825277.370, "dur": 2.304, + "args": { + "External id": 1430761,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825463.749, "dur": 2.548, + "args": { + "External id": 1430762,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850825470.883, "dur": 40.140, + "args": { + "External id": 1430763,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825486.190, "dur": 0.930, + "args": { + "External id": 1430764,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850825518.292, "dur": 34.627, + "args": { + "External id": 1430765,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850825520.435, "dur": 32.222, + "args": { + "External id": 1430766,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825524.781, "dur": 6.813, + "args": { + "External id": 1430767,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850825536.151, "dur": 15.884, + "args": { + "External id": 1430768,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850825557.873, "dur": 5.172, + "args": { + "External id": 1430769,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825561.663, "dur": 1.231, + "args": { + "External id": 1430770,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825570.237, "dur": 4.514, + "args": { + "External id": 1430771,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825571.037, "dur": 3.604, + "args": { + "External id": 1430772,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825576.988, "dur": 4.629, + "args": { + "External id": 1430773,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825579.975, "dur": 1.527, + "args": { + "External id": 1430774,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850825609.554, "dur": 19.533, + "args": { + "External id": 1430775,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850825641.871, "dur": 8.107, + "args": { + "External id": 1430776,"Record function id": 0, "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850825643.811, "dur": 5.415, + "args": { + "External id": 1430777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850825645.734, "dur": 2.578, + "args": { + "External id": 1430778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850825646.659, "dur": 1.527, + "args": { + "External id": 1430779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825654.236, "dur": 10.856, + "args": { + "External id": 1430780,"Record function id": 0, "Sequence number": 15348804, "Fwd thread id": 1, "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825655.231, "dur": 6.986, + "args": { + "External id": 1430781,"Sequence number": 15348804, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 764 + } + }, + { + "ph": "f", "id": 78, "pid": 2338706, "tid": 2379422, "ts": 6413850825655.231, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825657.203, "dur": 4.771, + "args": { + "External id": 1430782,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825660.417, "dur": 1.430, + "args": { + "External id": 1430783,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825669.038, "dur": 151.839, + "args": { + "External id": 1430784,"Record function id": 0, "Sequence number": 15348803, "Fwd thread id": 1, "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825670.006, "dur": 142.700, + "args": { + "External id": 1430785,"Sequence number": 15348803, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 768 + } + }, + { + "ph": "f", "id": 79, "pid": 2338706, "tid": 2379422, "ts": 6413850825670.006, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850825673.521, "dur": 4.728, + "args": { + "External id": 1430786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850825675.011, "dur": 2.656, + "args": { + "External id": 1430787,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825676.481, "dur": 1.029, + "args": { + "External id": 1430788,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850825679.471, "dur": 75.854, + "args": { + "External id": 1430789,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850825756.825, "dur": 9.787, + "args": { + "External id": 1430790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850825760.232, "dur": 5.668, + "args": { + "External id": 1430791,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825764.894, "dur": 0.865, + "args": { + "External id": 1430792,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850825768.162, "dur": 2.692, + "args": { + "External id": 1430793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850825768.811, "dur": 1.496, + "args": { + "External id": 1430794,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825769.792, "dur": 0.349, + "args": { + "External id": 1430795,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850825771.528, "dur": 40.105, + "args": { + "External id": 1430796,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825826.472, "dur": 14.437, + "args": { + "External id": 1430797,"Record function id": 0, "Sequence number": 15348802, "Fwd thread id": 1, "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825827.649, "dur": 10.740, + "args": { + "External id": 1430798,"Sequence number": 15348802, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 781 + } + }, + { + "ph": "f", "id": 80, "pid": 2338706, "tid": 2379422, "ts": 6413850825827.649, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825829.090, "dur": 9.119, + "args": { + "External id": 1430799,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825834.400, "dur": 3.638, + "args": { + "External id": 1430800,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825847.885, "dur": 8.146, + "args": { + "External id": 1430801,"Record function id": 0, "Sequence number": 15348801, "Fwd thread id": 1, "Ev Idx": 784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825849.167, "dur": 4.199, + "args": { + "External id": 1430802,"Sequence number": 15348801, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 785 + } + }, + { + "ph": "f", "id": 81, "pid": 2338706, "tid": 2379422, "ts": 6413850825849.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850825850.104, "dur": 3.005, + "args": { + "External id": 1430803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850825850.833, "dur": 1.752, + "args": { + "External id": 1430804,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825851.883, "dur": 0.578, + "args": { + "External id": 1430805,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850825860.617, "dur": 5.472, + "args": { + "External id": 1430806,"Record function id": 0, "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850825861.908, "dur": 3.636, + "args": { + "External id": 1430807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850825863.243, "dur": 2.030, + "args": { + "External id": 1430808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850825864.031, "dur": 1.106, + "args": { + "External id": 1430809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825869.698, "dur": 8.322, + "args": { + "External id": 1430810,"Record function id": 0, "Sequence number": 15348800, "Fwd thread id": 1, "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850825872.699, "dur": 3.274, + "args": { + "External id": 1430811,"Sequence number": 15348800, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 794 + } + }, + { + "ph": "f", "id": 82, "pid": 2338706, "tid": 2379422, "ts": 6413850825872.699, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850825873.760, "dur": 2.026, + "args": { + "External id": 1430812,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850825874.240, "dur": 1.378, + "args": { + "External id": 1430813,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850825882.662, "dur": 495.102, + "args": { + "External id": 1430814,"Record function id": 0, "Sequence number": 15348799, "Fwd thread id": 1, "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850825886.163, "dur": 469.064, + "args": { + "External id": 1430815,"Sequence number": 15348799, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 798 + } + }, + { + "ph": "f", "id": 83, "pid": 2338706, "tid": 2379422, "ts": 6413850825886.163, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850825902.407, "dur": 6.813, + "args": { + "External id": 1430816,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825904.760, "dur": 3.973, + "args": { + "External id": 1430817,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850825911.214, "dur": 6.704, + "args": { + "External id": 1430818,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825915.409, "dur": 2.228, + "args": { + "External id": 1430819,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850825919.460, "dur": 4.002, + "args": { + "External id": 1430820,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850825920.713, "dur": 2.484, + "args": { + "External id": 1430821,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850825956.680, "dur": 367.108, + "args": { + "External id": 1430822,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850826111.850, "dur": 6.305, + "args": { + "External id": 1430823,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850826124.919, "dur": 7.150, + "args": { + "External id": 1430824,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850826133.245, "dur": 3.977, + "args": { + "External id": 1430825,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850826138.390, "dur": 2.072, + "args": { + "External id": 1430826,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850826196.073, "dur": 3.150, + "args": { + "External id": 1430827,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850826197.225, "dur": 1.844, + "args": { + "External id": 1430828,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850826201.138, "dur": 37.729, + "args": { + "External id": 1430829,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826211.675, "dur": 1.572, + "args": { + "External id": 1430830,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850826240.270, "dur": 1.535, + "args": { + "External id": 1430831,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850826241.191, "dur": 0.534, + "args": { + "External id": 1430832,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850826245.278, "dur": 23.164, + "args": { + "External id": 1430833,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826246.823, "dur": 2.794, + "args": { + "External id": 1430834,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850826340.305, "dur": 4.297, + "args": { + "External id": 1430835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850826348.307, "dur": 0.779, + "args": { + "External id": 1430836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850826351.358, "dur": 0.521, + "args": { + "External id": 1430837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850826392.159, "dur": 271.283, + "args": { + "External id": 1430838,"Record function id": 0, "Sequence number": 15348798, "Fwd thread id": 1, "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850826394.375, "dur": 261.963, + "args": { + "External id": 1430839,"Sequence number": 15348798, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 822 + } + }, + { + "ph": "f", "id": 84, "pid": 2338706, "tid": 2379422, "ts": 6413850826394.375, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850826418.526, "dur": 54.988, + "args": { + "External id": 1430840,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826425.271, "dur": 4.418, + "args": { + "External id": 1430841,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850826431.244, "dur": 41.638, + "args": { + "External id": 1430842,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850826485.800, "dur": 5.307, + "args": { + "External id": 1430843,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826487.707, "dur": 3.011, + "args": { + "External id": 1430844,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850826671.342, "dur": 197.601, + "args": { + "External id": 1430845,"Record function id": 0, "Sequence number": 15348797, "Fwd thread id": 1, "Ev Idx": 828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850826673.301, "dur": 187.272, + "args": { + "External id": 1430846,"Sequence number": 15348797, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 829 + } + }, + { + "ph": "f", "id": 85, "pid": 2338706, "tid": 2379422, "ts": 6413850826673.301, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850826686.780, "dur": 61.309, + "args": { + "External id": 1430847,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826691.538, "dur": 6.589, + "args": { + "External id": 1430848,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850826702.072, "dur": 45.364, + "args": { + "External id": 1430849,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850826756.182, "dur": 4.409, + "args": { + "External id": 1430850,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826757.600, "dur": 2.605, + "args": { + "External id": 1430851,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826876.458, "dur": 16.259, + "args": { + "External id": 1430852,"Record function id": 0, "Sequence number": 15348796, "Fwd thread id": 1, "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826877.961, "dur": 11.381, + "args": { + "External id": 1430853,"Sequence number": 15348796, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 836 + } + }, + { + "ph": "f", "id": 86, "pid": 2338706, "tid": 2379422, "ts": 6413850826877.961, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850826880.778, "dur": 8.215, + "args": { + "External id": 1430854,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850826884.358, "dur": 4.432, + "args": { + "External id": 1430855,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826896.752, "dur": 9.067, + "args": { + "External id": 1430856,"Record function id": 0, "Sequence number": 15348795, "Fwd thread id": 1, "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826897.946, "dur": 5.719, + "args": { + "External id": 1430857,"Sequence number": 15348795, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 840 + } + }, + { + "ph": "f", "id": 87, "pid": 2338706, "tid": 2379422, "ts": 6413850826897.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850826899.276, "dur": 4.205, + "args": { + "External id": 1430858,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850826902.202, "dur": 1.107, + "args": { + "External id": 1430859,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826912.939, "dur": 8.356, + "args": { + "External id": 1430860,"Record function id": 0, "Sequence number": 15348794, "Fwd thread id": 1, "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826913.940, "dur": 5.188, + "args": { + "External id": 1430861,"Sequence number": 15348794, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 844 + } + }, + { + "ph": "f", "id": 88, "pid": 2338706, "tid": 2379422, "ts": 6413850826913.940, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850826914.996, "dur": 3.966, + "args": { + "External id": 1430862,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850826917.900, "dur": 0.965, + "args": { + "External id": 1430863,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826925.304, "dur": 5.990, + "args": { + "External id": 1430864,"Record function id": 0, "Sequence number": 15348793, "Fwd thread id": 1, "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826926.207, "dur": 3.081, + "args": { + "External id": 1430865,"Sequence number": 15348793, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 848 + } + }, + { + "ph": "f", "id": 89, "pid": 2338706, "tid": 2379422, "ts": 6413850826926.207, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850826927.350, "dur": 1.756, + "args": { + "External id": 1430866,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850826928.075, "dur": 0.865, + "args": { + "External id": 1430867,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826935.404, "dur": 277.531, + "args": { + "External id": 1430868,"Record function id": 0, "Sequence number": 15348792, "Fwd thread id": 1, "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850826939.139, "dur": 263.498, + "args": { + "External id": 1430869,"Sequence number": 15348792, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 852 + } + }, + { + "ph": "f", "id": 90, "pid": 2338706, "tid": 2379422, "ts": 6413850826939.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850826943.389, "dur": 7.214, + "args": { + "External id": 1430870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850826945.481, "dur": 4.269, + "args": { + "External id": 1430871,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850826947.598, "dur": 1.776, + "args": { + "External id": 1430872,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850826952.403, "dur": 158.361, + "args": { + "External id": 1430873,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827114.354, "dur": 14.065, + "args": { + "External id": 1430874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827116.048, "dur": 11.016, + "args": { + "External id": 1430875,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827122.844, "dur": 3.937, + "args": { + "External id": 1430876,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827131.254, "dur": 3.703, + "args": { + "External id": 1430877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827132.795, "dur": 1.630, + "args": { + "External id": 1430878,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827133.958, "dur": 0.383, + "args": { + "External id": 1430879,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850827136.069, "dur": 65.536, + "args": { + "External id": 1430880,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827223.765, "dur": 14.537, + "args": { + "External id": 1430881,"Record function id": 0, "Sequence number": 15348791, "Fwd thread id": 1, "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827225.094, "dur": 10.864, + "args": { + "External id": 1430882,"Sequence number": 15348791, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 865 + } + }, + { + "ph": "f", "id": 91, "pid": 2338706, "tid": 2379422, "ts": 6413850827225.094, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850827229.819, "dur": 5.966, + "args": { + "External id": 1430883,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850827233.295, "dur": 2.237, + "args": { + "External id": 1430884,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827242.268, "dur": 8.134, + "args": { + "External id": 1430885,"Record function id": 0, "Sequence number": 15348790, "Fwd thread id": 1, "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827243.315, "dur": 4.734, + "args": { + "External id": 1430886,"Sequence number": 15348790, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 869 + } + }, + { + "ph": "f", "id": 92, "pid": 2338706, "tid": 2379422, "ts": 6413850827243.315, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827244.469, "dur": 3.327, + "args": { + "External id": 1430887,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827245.271, "dur": 1.972, + "args": { + "External id": 1430888,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827246.414, "dur": 0.679, + "args": { + "External id": 1430889,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850827257.128, "dur": 12.993, + "args": { + "External id": 1430890,"Record function id": 0, "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850827258.882, "dur": 10.319, + "args": { + "External id": 1430891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850827262.044, "dur": 6.710, + "args": { + "External id": 1430892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850827265.819, "dur": 2.822, + "args": { + "External id": 1430893,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827273.817, "dur": 9.802, + "args": { + "External id": 1430894,"Record function id": 0, "Sequence number": 15348789, "Fwd thread id": 1, "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827275.256, "dur": 5.963, + "args": { + "External id": 1430895,"Sequence number": 15348789, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 878 + } + }, + { + "ph": "f", "id": 93, "pid": 2338706, "tid": 2379422, "ts": 6413850827275.256, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850827276.476, "dur": 4.555, + "args": { + "External id": 1430896,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850827279.626, "dur": 1.308, + "args": { + "External id": 1430897,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827287.393, "dur": 126.472, + "args": { + "External id": 1430898,"Record function id": 0, "Sequence number": 15348788, "Fwd thread id": 1, "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827288.379, "dur": 117.396, + "args": { + "External id": 1430899,"Sequence number": 15348788, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 882 + } + }, + { + "ph": "f", "id": 94, "pid": 2338706, "tid": 2379422, "ts": 6413850827288.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827290.665, "dur": 5.345, + "args": { + "External id": 1430900,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827293.775, "dur": 1.758, + "args": { + "External id": 1430901,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827294.645, "dur": 0.702, + "args": { + "External id": 1430902,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850827296.888, "dur": 38.123, + "args": { + "External id": 1430903,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827336.468, "dur": 13.994, + "args": { + "External id": 1430904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827344.577, "dur": 5.289, + "args": { + "External id": 1430905,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827345.772, "dur": 3.930, + "args": { + "External id": 1430906,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827354.451, "dur": 5.428, + "args": { + "External id": 1430907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827354.954, "dur": 4.444, + "args": { + "External id": 1430908,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827358.873, "dur": 0.420, + "args": { + "External id": 1430909,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850827360.498, "dur": 44.405, + "args": { + "External id": 1430910,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827419.583, "dur": 60.571, + "args": { + "External id": 1430911,"Record function id": 0, "Sequence number": 15348787, "Fwd thread id": 1, "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827420.766, "dur": 4.204, + "args": { + "External id": 1430912,"Sequence number": 15348787, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 895 + } + }, + { + "ph": "f", "id": 95, "pid": 2338706, "tid": 2379422, "ts": 6413850827420.766, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850827422.521, "dur": 2.262, + "args": { + "External id": 1430913,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850827423.286, "dur": 1.314, + "args": { + "External id": 1430914,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850827446.722, "dur": 30.225, + "args": { + "External id": 1430915,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827487.540, "dur": 28.677, + "args": { + "External id": 1430916,"Record function id": 0, "Sequence number": 15348786, "Fwd thread id": 1, "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827491.030, "dur": 21.708, + "args": { + "External id": 1430917,"Sequence number": 15348786, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 900 + } + }, + { + "ph": "f", "id": 96, "pid": 2338706, "tid": 2379422, "ts": 6413850827491.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827491.948, "dur": 20.499, + "args": { + "External id": 1430918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827493.281, "dur": 18.389, + "args": { + "External id": 1430919,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827510.513, "dur": 0.804, + "args": { + "External id": 1430920,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850827521.282, "dur": 8.592, + "args": { + "External id": 1430921,"Record function id": 0, "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850827522.528, "dur": 6.671, + "args": { + "External id": 1430922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850827524.360, "dur": 4.408, + "args": { + "External id": 1430923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850827524.923, "dur": 3.711, + "args": { + "External id": 1430924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827536.012, "dur": 8.641, + "args": { + "External id": 1430925,"Record function id": 0, "Sequence number": 15348785, "Fwd thread id": 1, "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827536.883, "dur": 5.877, + "args": { + "External id": 1430926,"Sequence number": 15348785, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 909 + } + }, + { + "ph": "f", "id": 97, "pid": 2338706, "tid": 2379422, "ts": 6413850827536.883, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850827537.948, "dur": 4.628, + "args": { + "External id": 1430927,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850827541.155, "dur": 1.311, + "args": { + "External id": 1430928,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827548.303, "dur": 115.533, + "args": { + "External id": 1430929,"Record function id": 0, "Sequence number": 15348784, "Fwd thread id": 1, "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827549.360, "dur": 106.558, + "args": { + "External id": 1430930,"Sequence number": 15348784, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 913 + } + }, + { + "ph": "f", "id": 98, "pid": 2338706, "tid": 2379422, "ts": 6413850827549.360, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827552.024, "dur": 2.511, + "args": { + "External id": 1430931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827552.586, "dur": 1.472, + "args": { + "External id": 1430932,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827553.308, "dur": 0.523, + "args": { + "External id": 1430933,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850827557.726, "dur": 44.592, + "args": { + "External id": 1430934,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827603.803, "dur": 5.450, + "args": { + "External id": 1430935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827604.495, "dur": 4.086, + "args": { + "External id": 1430936,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827607.887, "dur": 0.559, + "args": { + "External id": 1430937,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827610.478, "dur": 5.404, + "args": { + "External id": 1430938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827611.197, "dur": 4.158, + "args": { + "External id": 1430939,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827614.976, "dur": 0.302, + "args": { + "External id": 1430940,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850827616.432, "dur": 38.597, + "args": { + "External id": 1430941,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827668.929, "dur": 31.007, + "args": { + "External id": 1430942,"Record function id": 0, "Sequence number": 15348783, "Fwd thread id": 1, "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827670.099, "dur": 6.013, + "args": { + "External id": 1430943,"Sequence number": 15348783, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 926 + } + }, + { + "ph": "f", "id": 99, "pid": 2338706, "tid": 2379422, "ts": 6413850827670.099, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850827671.300, "dur": 4.623, + "args": { + "External id": 1430944,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850827674.563, "dur": 1.216, + "args": { + "External id": 1430945,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850827678.722, "dur": 18.554, + "args": { + "External id": 1430946,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827704.428, "dur": 13.251, + "args": { + "External id": 1430947,"Record function id": 0, "Sequence number": 15348782, "Fwd thread id": 1, "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850827705.258, "dur": 10.281, + "args": { + "External id": 1430948,"Sequence number": 15348782, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 931 + } + }, + { + "ph": "f", "id": 100, "pid": 2338706, "tid": 2379422, "ts": 6413850827705.258, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850827706.319, "dur": 8.982, + "args": { + "External id": 1430949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850827707.182, "dur": 7.500, + "args": { + "External id": 1430950,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850827711.259, "dur": 3.288, + "args": { + "External id": 1430951,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850827722.117, "dur": 5.887, + "args": { + "External id": 1430952,"Record function id": 0, "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850827723.482, "dur": 3.921, + "args": { + "External id": 1430953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850827724.708, "dur": 2.348, + "args": { + "External id": 1430954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850827725.712, "dur": 1.216, + "args": { + "External id": 1430955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850827733.154, "dur": 504.126, + "args": { + "External id": 1430956,"Record function id": 0, "Sequence number": 15348781, "Fwd thread id": 1, "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850827734.512, "dur": 466.167, + "args": { + "External id": 1430957,"Sequence number": 15348781, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 940 + } + }, + { + "ph": "f", "id": 101, "pid": 2338706, "tid": 2379422, "ts": 6413850827734.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850827779.588, "dur": 2.191, + "args": { + "External id": 1430958,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850827780.433, "dur": 1.161, + "args": { + "External id": 1430959,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850827801.975, "dur": 4.563, + "args": { + "External id": 1430960,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850827818.992, "dur": 2.768, + "args": { + "External id": 1430961,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828022.346, "dur": 3.879, + "args": { + "External id": 1430962,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850828031.513, "dur": 85.374, + "args": { + "External id": 1430963,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828048.455, "dur": 1.135, + "args": { + "External id": 1430964,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850828127.093, "dur": 36.401, + "args": { + "External id": 1430965,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850828129.127, "dur": 34.075, + "args": { + "External id": 1430966,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828134.234, "dur": 7.376, + "args": { + "External id": 1430967,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850828143.820, "dur": 18.789, + "args": { + "External id": 1430968,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850828172.544, "dur": 6.579, + "args": { + "External id": 1430969,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828174.289, "dur": 4.673, + "args": { + "External id": 1430970,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850828189.564, "dur": 1.955, + "args": { + "External id": 1430971,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828190.415, "dur": 0.990, + "args": { + "External id": 1430972,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850828213.546, "dur": 19.349, + "args": { + "External id": 1430973,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850828255.775, "dur": 10.591, + "args": { + "External id": 1430974,"Record function id": 0, "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850828258.345, "dur": 7.095, + "args": { + "External id": 1430975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850828261.017, "dur": 3.387, + "args": { + "External id": 1430976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850828262.300, "dur": 1.974, + "args": { + "External id": 1430977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850828270.589, "dur": 6.953, + "args": { + "External id": 1430978,"Record function id": 0, "Sequence number": 15348780, "Fwd thread id": 1, "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850828272.201, "dur": 1.707, + "args": { + "External id": 1430979,"Sequence number": 15348780, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 962 + } + }, + { + "ph": "f", "id": 102, "pid": 2338706, "tid": 2379422, "ts": 6413850828272.201, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850828281.887, "dur": 482.625, + "args": { + "External id": 1430980,"Record function id": 0, "Sequence number": 15348779, "Fwd thread id": 1, "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850828283.375, "dur": 469.131, + "args": { + "External id": 1430981,"Sequence number": 15348779, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 964 + } + }, + { + "ph": "f", "id": 103, "pid": 2338706, "tid": 2379422, "ts": 6413850828283.375, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850828318.310, "dur": 11.672, + "args": { + "External id": 1430982,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850828326.042, "dur": 3.602, + "args": { + "External id": 1430983,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850828336.169, "dur": 5.995, + "args": { + "External id": 1430984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850828338.169, "dur": 3.212, + "args": { + "External id": 1430985,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828340.084, "dur": 1.076, + "args": { + "External id": 1430986,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413850828346.522, "dur": 104.148, + "args": { + "External id": 1430987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850828347.539, "dur": 5.105, + "args": { + "External id": 1430988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850828348.261, "dur": 3.868, + "args": { + "External id": 1430989,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828351.451, "dur": 0.591, + "args": { + "External id": 1430990,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413850828353.984, "dur": 96.159, + "args": { + "External id": 1430991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850828355.637, "dur": 93.581, + "args": { + "External id": 1430992,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850828455.373, "dur": 5.923, + "args": { + "External id": 1430993,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828459.453, "dur": 1.723, + "args": { + "External id": 1430994,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850828500.676, "dur": 6.756, + "args": { + "External id": 1430995,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850828508.715, "dur": 4.980, + "args": { + "External id": 1430996,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850828516.735, "dur": 1.988, + "args": { + "External id": 1430997,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850828555.590, "dur": 2.279, + "args": { + "External id": 1430998,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828556.514, "dur": 1.172, + "args": { + "External id": 1430999,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413850828584.311, "dur": 147.170, + "args": { + "External id": 1431000,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850828589.865, "dur": 5.224, + "args": { + "External id": 1431001,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828593.287, "dur": 0.915, + "args": { + "External id": 1431002,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850828599.015, "dur": 7.276, + "args": { + "External id": 1431003,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828604.591, "dur": 0.694, + "args": { + "External id": 1431004,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850828607.867, "dur": 4.773, + "args": { + "External id": 1431005,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828611.538, "dur": 0.693, + "args": { + "External id": 1431006,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850828615.736, "dur": 4.947, + "args": { + "External id": 1431007,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828619.138, "dur": 0.846, + "args": { + "External id": 1431008,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850828624.746, "dur": 4.959, + "args": { + "External id": 1431009,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828628.798, "dur": 0.552, + "args": { + "External id": 1431010,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850828630.557, "dur": 10.341, + "args": { + "External id": 1431011,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850828636.120, "dur": 4.535, + "args": { + "External id": 1431012,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850828641.636, "dur": 1.981, + "args": { + "External id": 1431013,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828642.500, "dur": 0.798, + "args": { + "External id": 1431014,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850828646.765, "dur": 3.838, + "args": { + "External id": 1431015,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828647.334, "dur": 3.151, + "args": { + "External id": 1431016,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413850828654.289, "dur": 62.689, + "args": { + "External id": 1431017,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 1000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828719.233, "dur": 1.912, + "args": { + "External id": 1431018,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 1001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850828721.792, "dur": 5.162, + "args": { + "External id": 1431019,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 1002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828725.599, "dur": 0.526, + "args": { + "External id": 1431020,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 1003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828729.303, "dur": 1.048, + "args": { + "External id": 1431021,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 1004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850828774.656, "dur": 9.069, + "args": { + "External id": 1431022,"Record function id": 0, "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850828776.800, "dur": 6.199, + "args": { + "External id": 1431023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850828778.645, "dur": 3.324, + "args": { + "External id": 1431024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850828779.599, "dur": 2.245, + "args": { + "External id": 1431025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850828788.393, "dur": 12.660, + "args": { + "External id": 1431026,"Record function id": 0, "Sequence number": 15348778, "Fwd thread id": 1, "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850828789.516, "dur": 9.427, + "args": { + "External id": 1431027,"Sequence number": 15348778, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1010 + } + }, + { + "ph": "f", "id": 104, "pid": 2338706, "tid": 2379422, "ts": 6413850828789.516, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850828794.026, "dur": 4.681, + "args": { + "External id": 1431028,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850828797.245, "dur": 1.294, + "args": { + "External id": 1431029,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850828805.134, "dur": 303.616, + "args": { + "External id": 1431030,"Record function id": 0, "Sequence number": 15348777, "Fwd thread id": 1, "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850828806.066, "dur": 290.096, + "args": { + "External id": 1431031,"Sequence number": 15348777, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1014 + } + }, + { + "ph": "f", "id": 105, "pid": 2338706, "tid": 2379422, "ts": 6413850828806.066, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850828809.660, "dur": 8.596, + "args": { + "External id": 1431032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850828810.977, "dur": 6.682, + "args": { + "External id": 1431033,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828814.245, "dur": 3.252, + "args": { + "External id": 1431034,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850828819.327, "dur": 46.790, + "args": { + "External id": 1431035,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850828867.651, "dur": 3.729, + "args": { + "External id": 1431036,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850828868.367, "dur": 2.233, + "args": { + "External id": 1431037,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828869.470, "dur": 0.941, + "args": { + "External id": 1431038,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850828873.040, "dur": 129.118, + "args": { + "External id": 1431039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850828874.181, "dur": 125.719, + "args": { + "External id": 1431040,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850828997.952, "dur": 1.189, + "args": { + "External id": 1431041,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850829003.801, "dur": 90.325, + "args": { + "External id": 1431042,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829121.669, "dur": 9.712, + "args": { + "External id": 1431043,"Record function id": 0, "Sequence number": 15348776, "Fwd thread id": 1, "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829123.537, "dur": 5.983, + "args": { + "External id": 1431044,"Sequence number": 15348776, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1027 + } + }, + { + "ph": "f", "id": 106, "pid": 2338706, "tid": 2379422, "ts": 6413850829123.537, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829125.899, "dur": 3.435, + "args": { + "External id": 1431045,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829126.943, "dur": 2.279, + "args": { + "External id": 1431046,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829135.412, "dur": 11.178, + "args": { + "External id": 1431047,"Record function id": 0, "Sequence number": 15348775, "Fwd thread id": 1, "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829136.455, "dur": 8.065, + "args": { + "External id": 1431048,"Sequence number": 15348775, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1031 + } + }, + { + "ph": "f", "id": 107, "pid": 2338706, "tid": 2379422, "ts": 6413850829136.455, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850829137.490, "dur": 6.786, + "args": { + "External id": 1431049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850829138.610, "dur": 5.076, + "args": { + "External id": 1431050,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829142.799, "dur": 0.700, + "args": { + "External id": 1431051,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850829153.985, "dur": 10.171, + "args": { + "External id": 1431052,"Record function id": 0, "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850829155.542, "dur": 8.014, + "args": { + "External id": 1431053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850829157.490, "dur": 5.719, + "args": { + "External id": 1431054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850829158.271, "dur": 4.837, + "args": { + "External id": 1431055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829167.946, "dur": 6.397, + "args": { + "External id": 1431056,"Record function id": 0, "Sequence number": 15348774, "Fwd thread id": 1, "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829169.150, "dur": 3.116, + "args": { + "External id": 1431057,"Sequence number": 15348774, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1040 + } + }, + { + "ph": "f", "id": 108, "pid": 2338706, "tid": 2379422, "ts": 6413850829169.150, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829170.303, "dur": 1.780, + "args": { + "External id": 1431058,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829170.893, "dur": 1.092, + "args": { + "External id": 1431059,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829177.958, "dur": 157.946, + "args": { + "External id": 1431060,"Record function id": 0, "Sequence number": 15348773, "Fwd thread id": 1, "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829181.550, "dur": 145.122, + "args": { + "External id": 1431061,"Sequence number": 15348773, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1044 + } + }, + { + "ph": "f", "id": 109, "pid": 2338706, "tid": 2379422, "ts": 6413850829181.550, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850829183.726, "dur": 2.527, + "args": { + "External id": 1431062,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850829184.225, "dur": 1.529, + "args": { + "External id": 1431063,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829185.005, "dur": 0.621, + "args": { + "External id": 1431064,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850829187.102, "dur": 69.884, + "args": { + "External id": 1431065,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850829258.240, "dur": 8.362, + "args": { + "External id": 1431066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850829258.834, "dur": 7.183, + "args": { + "External id": 1431067,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829264.901, "dur": 0.968, + "args": { + "External id": 1431068,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850829267.683, "dur": 3.022, + "args": { + "External id": 1431069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850829268.984, "dur": 1.236, + "args": { + "External id": 1431070,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829269.639, "dur": 0.477, + "args": { + "External id": 1431071,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850829271.376, "dur": 54.534, + "args": { + "External id": 1431072,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829340.865, "dur": 45.073, + "args": { + "External id": 1431073,"Record function id": 0, "Sequence number": 15348772, "Fwd thread id": 1, "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829341.974, "dur": 8.697, + "args": { + "External id": 1431074,"Sequence number": 15348772, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1057 + } + }, + { + "ph": "f", "id": 110, "pid": 2338706, "tid": 2379422, "ts": 6413850829341.974, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829345.640, "dur": 4.841, + "args": { + "External id": 1431075,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829349.065, "dur": 1.277, + "args": { + "External id": 1431076,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850829354.262, "dur": 28.184, + "args": { + "External id": 1431077,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829390.528, "dur": 7.487, + "args": { + "External id": 1431078,"Record function id": 0, "Sequence number": 15348771, "Fwd thread id": 1, "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829391.383, "dur": 4.249, + "args": { + "External id": 1431079,"Sequence number": 15348771, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1062 + } + }, + { + "ph": "f", "id": 111, "pid": 2338706, "tid": 2379422, "ts": 6413850829391.383, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850829392.092, "dur": 3.335, + "args": { + "External id": 1431080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850829392.989, "dur": 1.830, + "args": { + "External id": 1431081,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829394.116, "dur": 0.529, + "args": { + "External id": 1431082,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850829402.813, "dur": 7.498, + "args": { + "External id": 1431083,"Record function id": 0, "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850829404.140, "dur": 5.611, + "args": { + "External id": 1431084,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850829405.067, "dur": 4.318, + "args": { + "External id": 1431085,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850829408.010, "dur": 1.238, + "args": { + "External id": 1431086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850829415.224, "dur": 482.293, + "args": { + "External id": 1431087,"Record function id": 0, "Sequence number": 15348770, "Fwd thread id": 1, "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850829416.511, "dur": 445.105, + "args": { + "External id": 1431088,"Sequence number": 15348770, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 1071 + } + }, + { + "ph": "f", "id": 112, "pid": 2338706, "tid": 2379422, "ts": 6413850829416.511, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413850829447.843, "dur": 42.440, + "args": { + "External id": 1431089,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850829449.558, "dur": 40.447, + "args": { + "External id": 1431090,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850829454.796, "dur": 7.133, + "args": { + "External id": 1431091,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 1074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850829457.787, "dur": 3.514, + "args": { + "External id": 1431092,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850829463.510, "dur": 25.913, + "args": { + "External id": 1431093,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829503.758, "dur": 2.086, + "args": { + "External id": 1431094,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829504.421, "dur": 1.243, + "args": { + "External id": 1431095,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829513.631, "dur": 1.323, + "args": { + "External id": 1431096,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829514.061, "dur": 0.774, + "args": { + "External id": 1431097,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850829529.975, "dur": 3.324, + "args": { + "External id": 1431098,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850829548.288, "dur": 2.513, + "args": { + "External id": 1431099,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829734.603, "dur": 4.638, + "args": { + "External id": 1431100,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850829744.195, "dur": 41.902, + "args": { + "External id": 1431101,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829759.081, "dur": 0.863, + "args": { + "External id": 1431102,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850829792.869, "dur": 32.714, + "args": { + "External id": 1431103,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850829795.327, "dur": 29.949, + "args": { + "External id": 1431104,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829799.875, "dur": 6.440, + "args": { + "External id": 1431105,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850829808.036, "dur": 16.656, + "args": { + "External id": 1431106,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850829830.661, "dur": 2.245, + "args": { + "External id": 1431107,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829831.594, "dur": 1.188, + "args": { + "External id": 1431108,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829842.184, "dur": 4.501, + "args": { + "External id": 1431109,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829845.179, "dur": 1.338, + "args": { + "External id": 1431110,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829848.953, "dur": 2.621, + "args": { + "External id": 1431111,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829849.989, "dur": 1.475, + "args": { + "External id": 1431112,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850829877.069, "dur": 18.765, + "args": { + "External id": 1431113,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850829908.462, "dur": 8.819, + "args": { + "External id": 1431114,"Record function id": 0, "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850829910.671, "dur": 5.931, + "args": { + "External id": 1431115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850829912.535, "dur": 2.949, + "args": { + "External id": 1431116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850829913.599, "dur": 1.752, + "args": { + "External id": 1431117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829921.854, "dur": 13.577, + "args": { + "External id": 1431118,"Record function id": 0, "Sequence number": 15348769, "Fwd thread id": 1, "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829923.076, "dur": 9.986, + "args": { + "External id": 1431119,"Sequence number": 15348769, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1102 + } + }, + { + "ph": "f", "id": 113, "pid": 2338706, "tid": 2379422, "ts": 6413850829923.076, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850829927.847, "dur": 4.996, + "args": { + "External id": 1431120,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850829931.243, "dur": 1.449, + "args": { + "External id": 1431121,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829939.972, "dur": 305.646, + "args": { + "External id": 1431122,"Record function id": 0, "Sequence number": 15348768, "Fwd thread id": 1, "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850829940.884, "dur": 293.629, + "args": { + "External id": 1431123,"Sequence number": 15348768, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1106 + } + }, + { + "ph": "f", "id": 114, "pid": 2338706, "tid": 2379422, "ts": 6413850829940.884, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850829943.722, "dur": 7.929, + "args": { + "External id": 1431124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850829945.126, "dur": 5.845, + "args": { + "External id": 1431125,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850829949.786, "dur": 0.976, + "args": { + "External id": 1431126,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850829952.951, "dur": 143.894, + "args": { + "External id": 1431127,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850830100.575, "dur": 5.748, + "args": { + "External id": 1431128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850830101.910, "dur": 3.439, + "args": { + "External id": 1431129,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830103.564, "dur": 1.625, + "args": { + "External id": 1431130,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850830108.511, "dur": 53.467, + "args": { + "External id": 1431131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850830152.562, "dur": 8.736, + "args": { + "External id": 1431132,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830157.637, "dur": 3.573, + "args": { + "External id": 1431133,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850830162.853, "dur": 70.489, + "args": { + "External id": 1431134,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850830257.506, "dur": 9.500, + "args": { + "External id": 1431135,"Record function id": 0, "Sequence number": 15348767, "Fwd thread id": 1, "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850830259.165, "dur": 5.239, + "args": { + "External id": 1431136,"Sequence number": 15348767, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1119 + } + }, + { + "ph": "f", "id": 115, "pid": 2338706, "tid": 2379422, "ts": 6413850830259.165, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850830261.250, "dur": 2.981, + "args": { + "External id": 1431137,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850830262.179, "dur": 1.873, + "args": { + "External id": 1431138,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850830271.006, "dur": 12.052, + "args": { + "External id": 1431139,"Record function id": 0, "Sequence number": 15348766, "Fwd thread id": 1, "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850830271.787, "dur": 9.276, + "args": { + "External id": 1431140,"Sequence number": 15348766, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1123 + } + }, + { + "ph": "f", "id": 116, "pid": 2338706, "tid": 2379422, "ts": 6413850830271.787, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850830272.681, "dur": 8.135, + "args": { + "External id": 1431141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850830273.675, "dur": 6.469, + "args": { + "External id": 1431142,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830279.644, "dur": 0.342, + "args": { + "External id": 1431143,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850830288.223, "dur": 7.907, + "args": { + "External id": 1431144,"Record function id": 0, "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850830289.781, "dur": 5.773, + "args": { + "External id": 1431145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850830292.138, "dur": 3.036, + "args": { + "External id": 1431146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850830293.106, "dur": 1.928, + "args": { + "External id": 1431147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850830300.059, "dur": 6.692, + "args": { + "External id": 1431148,"Record function id": 0, "Sequence number": 15348765, "Fwd thread id": 1, "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850830301.098, "dur": 3.603, + "args": { + "External id": 1431149,"Sequence number": 15348765, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1132 + } + }, + { + "ph": "f", "id": 117, "pid": 2338706, "tid": 2379422, "ts": 6413850830301.098, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850830302.327, "dur": 2.187, + "args": { + "External id": 1431150,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850830303.050, "dur": 1.283, + "args": { + "External id": 1431151,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850830311.459, "dur": 450.111, + "args": { + "External id": 1431152,"Record function id": 0, "Sequence number": 15348764, "Fwd thread id": 1, "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850830312.557, "dur": 428.820, + "args": { + "External id": 1431153,"Sequence number": 15348764, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1136 + } + }, + { + "ph": "f", "id": 118, "pid": 2338706, "tid": 2379422, "ts": 6413850830312.557, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850830331.352, "dur": 12.910, + "args": { + "External id": 1431154,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830338.812, "dur": 4.901, + "args": { + "External id": 1431155,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850830346.852, "dur": 3.382, + "args": { + "External id": 1431156,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830347.832, "dur": 1.992, + "args": { + "External id": 1431157,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850830359.674, "dur": 11.944, + "args": { + "External id": 1431158,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830363.162, "dur": 8.191, + "args": { + "External id": 1431159,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850830404.459, "dur": 306.233, + "args": { + "External id": 1431160,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850830501.902, "dur": 6.576, + "args": { + "External id": 1431161,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850830510.524, "dur": 2.917, + "args": { + "External id": 1431162,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850830516.785, "dur": 2.332, + "args": { + "External id": 1431163,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850830520.154, "dur": 4.112, + "args": { + "External id": 1431164,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850830591.849, "dur": 2.784, + "args": { + "External id": 1431165,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850830592.769, "dur": 1.661, + "args": { + "External id": 1431166,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850830599.116, "dur": 31.626, + "args": { + "External id": 1431167,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830604.159, "dur": 0.968, + "args": { + "External id": 1431168,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850830634.882, "dur": 1.287, + "args": { + "External id": 1431169,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850830635.382, "dur": 0.701, + "args": { + "External id": 1431170,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850830639.543, "dur": 18.814, + "args": { + "External id": 1431171,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830643.573, "dur": 0.460, + "args": { + "External id": 1431172,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850830726.479, "dur": 4.137, + "args": { + "External id": 1431173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850830734.127, "dur": 0.923, + "args": { + "External id": 1431174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850830737.297, "dur": 0.595, + "args": { + "External id": 1431175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850830772.257, "dur": 360.955, + "args": { + "External id": 1431176,"Record function id": 0, "Sequence number": 15348763, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850830774.278, "dur": 347.297, + "args": { + "External id": 1431177,"Sequence number": 15348763, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1160 + } + }, + { + "ph": "f", "id": 119, "pid": 2338706, "tid": 2379422, "ts": 6413850830774.278, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850830798.759, "dur": 56.922, + "args": { + "External id": 1431178,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830802.083, "dur": 6.637, + "args": { + "External id": 1431179,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850830810.578, "dur": 44.264, + "args": { + "External id": 1431180,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 1163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850830867.672, "dur": 7.160, + "args": { + "External id": 1431181,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850830871.892, "dur": 2.586, + "args": { + "External id": 1431182,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850831146.405, "dur": 221.488, + "args": { + "External id": 1431183,"Record function id": 0, "Sequence number": 15348762, "Fwd thread id": 1, "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850831148.847, "dur": 211.786, + "args": { + "External id": 1431184,"Sequence number": 15348762, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1167 + } + }, + { + "ph": "f", "id": 120, "pid": 2338706, "tid": 2379422, "ts": 6413850831148.847, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850831165.619, "dur": 59.743, + "args": { + "External id": 1431185,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831169.714, "dur": 5.404, + "args": { + "External id": 1431186,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850831176.706, "dur": 47.712, + "args": { + "External id": 1431187,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 1170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850831234.524, "dur": 9.081, + "args": { + "External id": 1431188,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831239.011, "dur": 4.141, + "args": { + "External id": 1431189,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831376.268, "dur": 14.353, + "args": { + "External id": 1431190,"Record function id": 0, "Sequence number": 15348761, "Fwd thread id": 1, "Ev Idx": 1173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831378.023, "dur": 9.784, + "args": { + "External id": 1431191,"Sequence number": 15348761, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1174 + } + }, + { + "ph": "f", "id": 121, "pid": 2338706, "tid": 2379422, "ts": 6413850831378.023, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831380.954, "dur": 6.548, + "args": { + "External id": 1431192,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831382.506, "dur": 4.739, + "args": { + "External id": 1431193,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831394.816, "dur": 9.024, + "args": { + "External id": 1431194,"Record function id": 0, "Sequence number": 15348760, "Fwd thread id": 1, "Ev Idx": 1177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831395.808, "dur": 6.195, + "args": { + "External id": 1431195,"Sequence number": 15348760, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1178 + } + }, + { + "ph": "f", "id": 122, "pid": 2338706, "tid": 2379422, "ts": 6413850831395.808, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831396.898, "dur": 4.907, + "args": { + "External id": 1431196,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831400.428, "dur": 1.232, + "args": { + "External id": 1431197,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831407.656, "dur": 8.862, + "args": { + "External id": 1431198,"Record function id": 0, "Sequence number": 15348759, "Fwd thread id": 1, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831408.652, "dur": 5.967, + "args": { + "External id": 1431199,"Sequence number": 15348759, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1182 + } + }, + { + "ph": "f", "id": 123, "pid": 2338706, "tid": 2379422, "ts": 6413850831408.652, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831409.918, "dur": 4.522, + "args": { + "External id": 1431200,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831413.212, "dur": 1.130, + "args": { + "External id": 1431201,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831420.316, "dur": 8.998, + "args": { + "External id": 1431202,"Record function id": 0, "Sequence number": 15348758, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831421.529, "dur": 5.807, + "args": { + "External id": 1431203,"Sequence number": 15348758, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1186 + } + }, + { + "ph": "f", "id": 124, "pid": 2338706, "tid": 2379422, "ts": 6413850831421.529, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831425.104, "dur": 2.049, + "args": { + "External id": 1431204,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831425.706, "dur": 1.339, + "args": { + "External id": 1431205,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831435.865, "dur": 201.679, + "args": { + "External id": 1431206,"Record function id": 0, "Sequence number": 15348757, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831436.980, "dur": 190.999, + "args": { + "External id": 1431207,"Sequence number": 15348757, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1190 + } + }, + { + "ph": "f", "id": 125, "pid": 2338706, "tid": 2379422, "ts": 6413850831436.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831441.463, "dur": 13.293, + "args": { + "External id": 1431208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831444.518, "dur": 9.388, + "args": { + "External id": 1431209,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831448.819, "dur": 4.671, + "args": { + "External id": 1431210,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850831456.803, "dur": 86.233, + "args": { + "External id": 1431211,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831544.609, "dur": 13.562, + "args": { + "External id": 1431212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831551.417, "dur": 5.711, + "args": { + "External id": 1431213,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831553.144, "dur": 3.683, + "args": { + "External id": 1431214,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831560.335, "dur": 9.552, + "args": { + "External id": 1431215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831561.993, "dur": 7.155, + "args": { + "External id": 1431216,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831568.363, "dur": 0.660, + "args": { + "External id": 1431217,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850831570.939, "dur": 55.879, + "args": { + "External id": 1431218,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831644.078, "dur": 7.271, + "args": { + "External id": 1431219,"Record function id": 0, "Sequence number": 15348756, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831645.288, "dur": 4.290, + "args": { + "External id": 1431220,"Sequence number": 15348756, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1203 + } + }, + { + "ph": "f", "id": 126, "pid": 2338706, "tid": 2379422, "ts": 6413850831645.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831646.856, "dur": 2.557, + "args": { + "External id": 1431221,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831647.764, "dur": 1.484, + "args": { + "External id": 1431222,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831655.166, "dur": 13.401, + "args": { + "External id": 1431223,"Record function id": 0, "Sequence number": 15348755, "Fwd thread id": 1, "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831656.031, "dur": 10.042, + "args": { + "External id": 1431224,"Sequence number": 15348755, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1207 + } + }, + { + "ph": "f", "id": 127, "pid": 2338706, "tid": 2379422, "ts": 6413850831656.031, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831657.638, "dur": 8.210, + "args": { + "External id": 1431225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831658.572, "dur": 6.710, + "args": { + "External id": 1431226,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831664.447, "dur": 0.637, + "args": { + "External id": 1431227,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850831675.738, "dur": 13.885, + "args": { + "External id": 1431228,"Record function id": 0, "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850831677.554, "dur": 11.054, + "args": { + "External id": 1431229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850831680.723, "dur": 7.305, + "args": { + "External id": 1431230,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850831682.074, "dur": 5.813, + "args": { + "External id": 1431231,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831693.268, "dur": 6.231, + "args": { + "External id": 1431232,"Record function id": 0, "Sequence number": 15348754, "Fwd thread id": 1, "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831694.633, "dur": 3.023, + "args": { + "External id": 1431233,"Sequence number": 15348754, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1216 + } + }, + { + "ph": "f", "id": 128, "pid": 2338706, "tid": 2379422, "ts": 6413850831694.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831695.627, "dur": 1.846, + "args": { + "External id": 1431234,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831696.425, "dur": 0.940, + "args": { + "External id": 1431235,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831703.275, "dur": 106.229, + "args": { + "External id": 1431236,"Record function id": 0, "Sequence number": 15348753, "Fwd thread id": 1, "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831704.379, "dur": 98.429, + "args": { + "External id": 1431237,"Sequence number": 15348753, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1220 + } + }, + { + "ph": "f", "id": 129, "pid": 2338706, "tid": 2379422, "ts": 6413850831704.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831709.037, "dur": 3.086, + "args": { + "External id": 1431238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831709.831, "dur": 1.812, + "args": { + "External id": 1431239,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831710.689, "dur": 0.810, + "args": { + "External id": 1431240,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850831712.841, "dur": 33.883, + "args": { + "External id": 1431241,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831747.834, "dur": 8.790, + "args": { + "External id": 1431242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831748.788, "dur": 7.210, + "args": { + "External id": 1431243,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831754.492, "dur": 1.344, + "args": { + "External id": 1431244,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831758.202, "dur": 3.490, + "args": { + "External id": 1431245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831759.579, "dur": 1.610, + "args": { + "External id": 1431246,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831760.702, "dur": 0.393, + "args": { + "External id": 1431247,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850831762.506, "dur": 39.308, + "args": { + "External id": 1431248,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831815.042, "dur": 41.262, + "args": { + "External id": 1431249,"Record function id": 0, "Sequence number": 15348752, "Fwd thread id": 1, "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831816.239, "dur": 6.291, + "args": { + "External id": 1431250,"Sequence number": 15348752, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1233 + } + }, + { + "ph": "f", "id": 130, "pid": 2338706, "tid": 2379422, "ts": 6413850831816.239, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831817.780, "dur": 4.582, + "args": { + "External id": 1431251,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831820.751, "dur": 1.468, + "args": { + "External id": 1431252,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850831826.504, "dur": 26.765, + "args": { + "External id": 1431253,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831861.161, "dur": 10.416, + "args": { + "External id": 1431254,"Record function id": 0, "Sequence number": 15348751, "Fwd thread id": 1, "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831864.984, "dur": 4.709, + "args": { + "External id": 1431255,"Sequence number": 15348751, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1238 + } + }, + { + "ph": "f", "id": 131, "pid": 2338706, "tid": 2379422, "ts": 6413850831864.984, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831866.338, "dur": 3.102, + "args": { + "External id": 1431256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831867.072, "dur": 1.812, + "args": { + "External id": 1431257,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831868.173, "dur": 0.580, + "args": { + "External id": 1431258,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850831876.149, "dur": 6.478, + "args": { + "External id": 1431259,"Record function id": 0, "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850831877.562, "dur": 4.484, + "args": { + "External id": 1431260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850831879.333, "dur": 2.178, + "args": { + "External id": 1431261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850831880.208, "dur": 1.200, + "args": { + "External id": 1431262,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831886.226, "dur": 10.514, + "args": { + "External id": 1431263,"Record function id": 0, "Sequence number": 15348750, "Fwd thread id": 1, "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831887.230, "dur": 7.780, + "args": { + "External id": 1431264,"Sequence number": 15348750, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1247 + } + }, + { + "ph": "f", "id": 132, "pid": 2338706, "tid": 2379422, "ts": 6413850831887.230, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850831890.736, "dur": 4.084, + "args": { + "External id": 1431265,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850831893.633, "dur": 1.052, + "args": { + "External id": 1431266,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831900.166, "dur": 141.353, + "args": { + "External id": 1431267,"Record function id": 0, "Sequence number": 15348749, "Fwd thread id": 1, "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850831901.147, "dur": 129.627, + "args": { + "External id": 1431268,"Sequence number": 15348749, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1251 + } + }, + { + "ph": "f", "id": 133, "pid": 2338706, "tid": 2379422, "ts": 6413850831901.147, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831903.777, "dur": 3.137, + "args": { + "External id": 1431269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831904.626, "dur": 1.794, + "args": { + "External id": 1431270,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831905.687, "dur": 0.590, + "args": { + "External id": 1431271,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850831907.780, "dur": 38.319, + "args": { + "External id": 1431272,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831950.612, "dur": 3.471, + "args": { + "External id": 1431273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831951.664, "dur": 1.861, + "args": { + "External id": 1431274,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831952.707, "dur": 0.661, + "args": { + "External id": 1431275,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850831955.397, "dur": 6.444, + "args": { + "External id": 1431276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850831956.844, "dur": 4.528, + "args": { + "External id": 1431277,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850831960.659, "dur": 0.596, + "args": { + "External id": 1431278,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850831964.807, "dur": 64.557, + "args": { + "External id": 1431279,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850832049.964, "dur": 75.332, + "args": { + "External id": 1431280,"Record function id": 0, "Sequence number": 15348748, "Fwd thread id": 1, "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850832051.325, "dur": 43.754, + "args": { + "External id": 1431281,"Sequence number": 15348748, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1264 + } + }, + { + "ph": "f", "id": 134, "pid": 2338706, "tid": 2379422, "ts": 6413850832051.325, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832053.431, "dur": 41.394, + "args": { + "External id": 1431282,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832054.289, "dur": 39.854, + "args": { + "External id": 1431283,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850832100.296, "dur": 21.290, + "args": { + "External id": 1431284,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850832131.866, "dur": 12.037, + "args": { + "External id": 1431285,"Record function id": 0, "Sequence number": 15348747, "Fwd thread id": 1, "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850832133.442, "dur": 8.421, + "args": { + "External id": 1431286,"Sequence number": 15348747, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1269 + } + }, + { + "ph": "f", "id": 135, "pid": 2338706, "tid": 2379422, "ts": 6413850832133.442, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850832134.434, "dur": 7.201, + "args": { + "External id": 1431287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850832135.741, "dur": 5.262, + "args": { + "External id": 1431288,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832140.228, "dur": 0.640, + "args": { + "External id": 1431289,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850832149.299, "dur": 7.297, + "args": { + "External id": 1431290,"Record function id": 0, "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850832150.954, "dur": 4.995, + "args": { + "External id": 1431291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850832152.666, "dur": 2.769, + "args": { + "External id": 1431292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850832153.671, "dur": 1.652, + "args": { + "External id": 1431293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850832164.602, "dur": 407.127, + "args": { + "External id": 1431294,"Record function id": 0, "Sequence number": 15348746, "Fwd thread id": 1, "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850832166.051, "dur": 372.230, + "args": { + "External id": 1431295,"Sequence number": 15348746, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1278 + } + }, + { + "ph": "f", "id": 136, "pid": 2338706, "tid": 2379422, "ts": 6413850832166.051, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832205.385, "dur": 5.017, + "args": { + "External id": 1431296,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832208.723, "dur": 1.548, + "args": { + "External id": 1431297,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850832227.726, "dur": 5.775, + "args": { + "External id": 1431298,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850832244.469, "dur": 2.298, + "args": { + "External id": 1431299,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832418.207, "dur": 2.178, + "args": { + "External id": 1431300,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850832425.274, "dur": 41.782, + "args": { + "External id": 1431301,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832438.436, "dur": 3.303, + "args": { + "External id": 1431302,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850832474.456, "dur": 38.584, + "args": { + "External id": 1431303,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850832476.629, "dur": 36.163, + "args": { + "External id": 1431304,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832485.479, "dur": 6.116, + "args": { + "External id": 1431305,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850832493.705, "dur": 18.387, + "args": { + "External id": 1431306,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850832518.229, "dur": 2.793, + "args": { + "External id": 1431307,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832519.363, "dur": 1.507, + "args": { + "External id": 1431308,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832528.725, "dur": 2.400, + "args": { + "External id": 1431309,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832529.595, "dur": 1.430, + "args": { + "External id": 1431310,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850832550.765, "dur": 16.998, + "args": { + "External id": 1431311,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850832581.654, "dur": 11.351, + "args": { + "External id": 1431312,"Record function id": 0, "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850832586.173, "dur": 6.044, + "args": { + "External id": 1431313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850832588.174, "dur": 2.746, + "args": { + "External id": 1431314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850832589.040, "dur": 1.767, + "args": { + "External id": 1431315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850832598.013, "dur": 6.058, + "args": { + "External id": 1431316,"Record function id": 0, "Sequence number": 15348745, "Fwd thread id": 1, "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850832599.688, "dur": 1.457, + "args": { + "External id": 1431317,"Sequence number": 15348745, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1300 + } + }, + { + "ph": "f", "id": 137, "pid": 2338706, "tid": 2379422, "ts": 6413850832599.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850832608.409, "dur": 551.942, + "args": { + "External id": 1431318,"Record function id": 0, "Sequence number": 15348744, "Fwd thread id": 1, "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850832609.649, "dur": 535.236, + "args": { + "External id": 1431319,"Sequence number": 15348744, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1302 + } + }, + { + "ph": "f", "id": 138, "pid": 2338706, "tid": 2379422, "ts": 6413850832609.649, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832645.169, "dur": 8.947, + "args": { + "External id": 1431320,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850832650.407, "dur": 3.393, + "args": { + "External id": 1431321,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 1304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850832657.620, "dur": 7.414, + "args": { + "External id": 1431322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850832659.068, "dur": 5.219, + "args": { + "External id": 1431323,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832663.220, "dur": 0.863, + "args": { + "External id": 1431324,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413850832669.105, "dur": 100.941, + "args": { + "External id": 1431325,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 1308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850832672.984, "dur": 3.323, + "args": { + "External id": 1431326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 1309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850832673.831, "dur": 1.938, + "args": { + "External id": 1431327,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832674.552, "dur": 1.088, + "args": { + "External id": 1431328,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413850832677.854, "dur": 91.735, + "args": { + "External id": 1431329,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 1312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850832679.667, "dur": 89.047, + "args": { + "External id": 1431330,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850832774.458, "dur": 2.573, + "args": { + "External id": 1431331,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 1314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832775.492, "dur": 1.380, + "args": { + "External id": 1431332,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 1315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850832815.950, "dur": 5.733, + "args": { + "External id": 1431333,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850832825.671, "dur": 5.050, + "args": { + "External id": 1431334,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850832831.464, "dur": 2.403, + "args": { + "External id": 1431335,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832865.801, "dur": 2.350, + "args": { + "External id": 1431336,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832866.499, "dur": 1.472, + "args": { + "External id": 1431337,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413850832894.509, "dur": 220.622, + "args": { + "External id": 1431338,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850832902.763, "dur": 8.046, + "args": { + "External id": 1431339,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832909.018, "dur": 0.971, + "args": { + "External id": 1431340,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850832912.222, "dur": 6.576, + "args": { + "External id": 1431341,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 1324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832917.268, "dur": 0.614, + "args": { + "External id": 1431342,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 1325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413850832920.357, "dur": 1.728, + "args": { + "External id": 1431343,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 1326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832921.276, "dur": 0.426, + "args": { + "External id": 1431344,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850832925.165, "dur": 2.518, + "args": { + "External id": 1431345,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 1328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832926.435, "dur": 0.485, + "args": { + "External id": 1431346,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 1329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850832933.609, "dur": 7.378, + "args": { + "External id": 1431347,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 1330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832937.825, "dur": 2.804, + "args": { + "External id": 1431348,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 1331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832942.201, "dur": 8.326, + "args": { + "External id": 1431349,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 1332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850832947.991, "dur": 2.289, + "args": { + "External id": 1431350,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 1333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850832951.526, "dur": 4.585, + "args": { + "External id": 1431351,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850832955.331, "dur": 0.425, + "args": { + "External id": 1431352,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 1335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850832959.019, "dur": 3.711, + "args": { + "External id": 1431353,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 1336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850832959.770, "dur": 2.851, + "args": { + "External id": 1431354,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 1337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413850832964.160, "dur": 88.142, + "args": { + "External id": 1431355,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833099.210, "dur": 2.423, + "args": { + "External id": 1431356,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 1339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413850833102.699, "dur": 6.894, + "args": { + "External id": 1431357,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 1340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833107.341, "dur": 1.124, + "args": { + "External id": 1431358,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 1341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833112.479, "dur": 1.208, + "args": { + "External id": 1431359,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 1342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850833176.220, "dur": 34.858, + "args": { + "External id": 1431360,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850833178.928, "dur": 31.250, + "args": { + "External id": 1431361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850833181.744, "dur": 27.323, + "args": { + "External id": 1431362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850833201.672, "dur": 7.189, + "args": { + "External id": 1431363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833216.120, "dur": 7.995, + "args": { + "External id": 1431364,"Record function id": 0, "Sequence number": 15348743, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833217.219, "dur": 4.165, + "args": { + "External id": 1431365,"Sequence number": 15348743, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1348 + } + }, + { + "ph": "f", "id": 139, "pid": 2338706, "tid": 2379422, "ts": 6413850833217.219, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850833219.107, "dur": 1.989, + "args": { + "External id": 1431366,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833219.685, "dur": 1.258, + "args": { + "External id": 1431367,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833228.332, "dur": 142.813, + "args": { + "External id": 1431368,"Record function id": 0, "Sequence number": 15348742, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833231.615, "dur": 131.051, + "args": { + "External id": 1431369,"Sequence number": 15348742, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1352 + } + }, + { + "ph": "f", "id": 140, "pid": 2338706, "tid": 2379422, "ts": 6413850833231.615, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833235.718, "dur": 4.120, + "args": { + "External id": 1431370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833237.227, "dur": 2.016, + "args": { + "External id": 1431371,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833238.427, "dur": 0.606, + "args": { + "External id": 1431372,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850833241.130, "dur": 62.200, + "args": { + "External id": 1431373,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833304.817, "dur": 9.605, + "args": { + "External id": 1431374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833305.641, "dur": 7.590, + "args": { + "External id": 1431375,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833311.933, "dur": 1.097, + "args": { + "External id": 1431376,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833316.059, "dur": 3.264, + "args": { + "External id": 1431377,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833317.573, "dur": 1.173, + "args": { + "External id": 1431378,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833318.372, "dur": 0.294, + "args": { + "External id": 1431379,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850833320.010, "dur": 41.576, + "args": { + "External id": 1431380,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833377.149, "dur": 9.524, + "args": { + "External id": 1431381,"Record function id": 0, "Sequence number": 15348741, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833378.323, "dur": 6.972, + "args": { + "External id": 1431382,"Sequence number": 15348741, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1365 + } + }, + { + "ph": "f", "id": 141, "pid": 2338706, "tid": 2379422, "ts": 6413850833378.323, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850833379.834, "dur": 5.274, + "args": { + "External id": 1431383,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833383.640, "dur": 1.289, + "args": { + "External id": 1431384,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833391.030, "dur": 11.373, + "args": { + "External id": 1431385,"Record function id": 0, "Sequence number": 15348740, "Fwd thread id": 1, "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833391.887, "dur": 8.327, + "args": { + "External id": 1431386,"Sequence number": 15348740, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1369 + } + }, + { + "ph": "f", "id": 142, "pid": 2338706, "tid": 2379422, "ts": 6413850833391.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833394.739, "dur": 5.256, + "args": { + "External id": 1431387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833395.322, "dur": 4.096, + "args": { + "External id": 1431388,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833396.435, "dur": 2.857, + "args": { + "External id": 1431389,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850833407.014, "dur": 5.701, + "args": { + "External id": 1431390,"Record function id": 0, "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850833408.647, "dur": 3.493, + "args": { + "External id": 1431391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850833409.855, "dur": 1.906, + "args": { + "External id": 1431392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850833410.451, "dur": 1.177, + "args": { + "External id": 1431393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833416.626, "dur": 7.634, + "args": { + "External id": 1431394,"Record function id": 0, "Sequence number": 15348739, "Fwd thread id": 1, "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833417.815, "dur": 4.799, + "args": { + "External id": 1431395,"Sequence number": 15348739, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 1378 + } + }, + { + "ph": "f", "id": 143, "pid": 2338706, "tid": 2379422, "ts": 6413850833417.815, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850833420.960, "dur": 1.478, + "args": { + "External id": 1431396,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833421.385, "dur": 0.950, + "args": { + "External id": 1431397,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 1380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833428.254, "dur": 107.387, + "args": { + "External id": 1431398,"Record function id": 0, "Sequence number": 15348738, "Fwd thread id": 1, "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833431.106, "dur": 96.730, + "args": { + "External id": 1431399,"Sequence number": 15348738, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1382 + } + }, + { + "ph": "f", "id": 144, "pid": 2338706, "tid": 2379422, "ts": 6413850833431.106, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833433.151, "dur": 2.575, + "args": { + "External id": 1431400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 1383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833433.913, "dur": 1.314, + "args": { + "External id": 1431401,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 1384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833434.758, "dur": 0.342, + "args": { + "External id": 1431402,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 1385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850833436.431, "dur": 37.706, + "args": { + "External id": 1431403,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 1386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833475.280, "dur": 6.245, + "args": { + "External id": 1431404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833476.028, "dur": 4.833, + "args": { + "External id": 1431405,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 1388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833479.574, "dur": 1.116, + "args": { + "External id": 1431406,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 1389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833482.842, "dur": 6.219, + "args": { + "External id": 1431407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833484.221, "dur": 4.325, + "args": { + "External id": 1431408,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833488.028, "dur": 0.440, + "args": { + "External id": 1431409,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850833489.488, "dur": 37.638, + "args": { + "External id": 1431410,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 1393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833543.306, "dur": 38.866, + "args": { + "External id": 1431411,"Record function id": 0, "Sequence number": 15348737, "Fwd thread id": 1, "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833544.403, "dur": 6.272, + "args": { + "External id": 1431412,"Sequence number": 15348737, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1395 + } + }, + { + "ph": "f", "id": 145, "pid": 2338706, "tid": 2379422, "ts": 6413850833544.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850833545.639, "dur": 4.873, + "args": { + "External id": 1431413,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833546.649, "dur": 3.666, + "args": { + "External id": 1431414,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850833554.295, "dur": 24.047, + "args": { + "External id": 1431415,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833586.715, "dur": 13.000, + "args": { + "External id": 1431416,"Record function id": 0, "Sequence number": 15348736, "Fwd thread id": 1, "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850833590.226, "dur": 7.460, + "args": { + "External id": 1431417,"Sequence number": 15348736, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1400 + } + }, + { + "ph": "f", "id": 146, "pid": 2338706, "tid": 2379422, "ts": 6413850833590.226, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850833591.481, "dur": 5.948, + "args": { + "External id": 1431418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 1401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850833592.390, "dur": 4.438, + "args": { + "External id": 1431419,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 1402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833595.569, "dur": 1.136, + "args": { + "External id": 1431420,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 1403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850833604.249, "dur": 5.410, + "args": { + "External id": 1431421,"Record function id": 0, "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850833605.719, "dur": 3.346, + "args": { + "External id": 1431422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850833606.675, "dur": 2.049, + "args": { + "External id": 1431423,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850833607.292, "dur": 1.314, + "args": { + "External id": 1431424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850833614.002, "dur": 570.406, + "args": { + "External id": 1431425,"Record function id": 0, "Sequence number": 15348735, "Fwd thread id": 1, "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850833615.445, "dur": 523.092, + "args": { + "External id": 1431426,"Sequence number": 15348735, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 1409 + } + }, + { + "ph": "f", "id": 147, "pid": 2338706, "tid": 2379422, "ts": 6413850833615.445, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413850833643.182, "dur": 39.694, + "args": { + "External id": 1431427,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850833644.868, "dur": 37.736, + "args": { + "External id": 1431428,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850833647.956, "dur": 7.130, + "args": { + "External id": 1431429,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 1412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850833650.890, "dur": 3.566, + "args": { + "External id": 1431430,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850833656.921, "dur": 25.090, + "args": { + "External id": 1431431,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850833700.491, "dur": 2.379, + "args": { + "External id": 1431432,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833701.503, "dur": 1.247, + "args": { + "External id": 1431433,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850833707.669, "dur": 1.674, + "args": { + "External id": 1431434,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833708.421, "dur": 0.753, + "args": { + "External id": 1431435,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850833725.676, "dur": 2.677, + "args": { + "External id": 1431436,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850833741.103, "dur": 5.612, + "args": { + "External id": 1431437,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850833927.969, "dur": 3.069, + "args": { + "External id": 1431438,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850833938.606, "dur": 58.960, + "args": { + "External id": 1431439,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850833949.184, "dur": 0.889, + "args": { + "External id": 1431440,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850834007.036, "dur": 44.303, + "args": { + "External id": 1431441,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850834009.163, "dur": 41.910, + "args": { + "External id": 1431442,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834019.070, "dur": 5.135, + "args": { + "External id": 1431443,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850834025.820, "dur": 24.640, + "args": { + "External id": 1431444,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850834097.319, "dur": 4.329, + "args": { + "External id": 1431445,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834098.812, "dur": 2.521, + "args": { + "External id": 1431446,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834112.565, "dur": 2.817, + "args": { + "External id": 1431447,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834113.807, "dur": 1.419, + "args": { + "External id": 1431448,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834117.521, "dur": 7.381, + "args": { + "External id": 1431449,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834123.007, "dur": 1.773, + "args": { + "External id": 1431450,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850834159.520, "dur": 22.487, + "args": { + "External id": 1431451,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850834201.229, "dur": 11.572, + "args": { + "External id": 1431452,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850834203.921, "dur": 7.940, + "args": { + "External id": 1431453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850834206.946, "dur": 3.899, + "args": { + "External id": 1431454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850834208.394, "dur": 2.272, + "args": { + "External id": 1431455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834217.574, "dur": 8.773, + "args": { + "External id": 1431456,"Record function id": 0, "Sequence number": 15348734, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834218.603, "dur": 4.811, + "args": { + "External id": 1431457,"Sequence number": 15348734, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1440 + } + }, + { + "ph": "f", "id": 148, "pid": 2338706, "tid": 2379422, "ts": 6413850834218.603, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834220.794, "dur": 2.306, + "args": { + "External id": 1431458,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834221.567, "dur": 1.360, + "args": { + "External id": 1431459,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834230.281, "dur": 168.330, + "args": { + "External id": 1431460,"Record function id": 0, "Sequence number": 15348733, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834231.439, "dur": 159.848, + "args": { + "External id": 1431461,"Sequence number": 15348733, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1444 + } + }, + { + "ph": "f", "id": 149, "pid": 2338706, "tid": 2379422, "ts": 6413850834231.439, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850834235.682, "dur": 8.528, + "args": { + "External id": 1431462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850834240.141, "dur": 3.320, + "args": { + "External id": 1431463,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834241.901, "dur": 1.281, + "args": { + "External id": 1431464,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850834245.343, "dur": 83.624, + "args": { + "External id": 1431465,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850834330.520, "dur": 9.611, + "args": { + "External id": 1431466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850834331.777, "dur": 7.505, + "args": { + "External id": 1431467,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834335.332, "dur": 3.797, + "args": { + "External id": 1431468,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850834342.440, "dur": 5.522, + "args": { + "External id": 1431469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850834345.847, "dur": 1.556, + "args": { + "External id": 1431470,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834346.674, "dur": 0.629, + "args": { + "External id": 1431471,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850834348.535, "dur": 41.741, + "args": { + "External id": 1431472,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834404.700, "dur": 9.837, + "args": { + "External id": 1431473,"Record function id": 0, "Sequence number": 15348732, "Fwd thread id": 1, "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834405.747, "dur": 6.399, + "args": { + "External id": 1431474,"Sequence number": 15348732, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1457 + } + }, + { + "ph": "f", "id": 150, "pid": 2338706, "tid": 2379422, "ts": 6413850834405.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834407.016, "dur": 4.950, + "args": { + "External id": 1431475,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834410.366, "dur": 1.436, + "args": { + "External id": 1431476,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834420.856, "dur": 10.989, + "args": { + "External id": 1431477,"Record function id": 0, "Sequence number": 15348731, "Fwd thread id": 1, "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834421.818, "dur": 7.194, + "args": { + "External id": 1431478,"Sequence number": 15348731, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1461 + } + }, + { + "ph": "f", "id": 151, "pid": 2338706, "tid": 2379422, "ts": 6413850834421.818, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850834422.871, "dur": 5.911, + "args": { + "External id": 1431479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850834423.546, "dur": 4.678, + "args": { + "External id": 1431480,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834427.343, "dur": 0.735, + "args": { + "External id": 1431481,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850834436.442, "dur": 6.673, + "args": { + "External id": 1431482,"Record function id": 0, "Ev Idx": 1465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850834437.991, "dur": 4.563, + "args": { + "External id": 1431483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850834439.339, "dur": 2.934, + "args": { + "External id": 1431484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850834440.136, "dur": 2.000, + "args": { + "External id": 1431485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834446.647, "dur": 6.239, + "args": { + "External id": 1431486,"Record function id": 0, "Sequence number": 15348730, "Fwd thread id": 1, "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850834447.861, "dur": 3.093, + "args": { + "External id": 1431487,"Sequence number": 15348730, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1470 + } + }, + { + "ph": "f", "id": 152, "pid": 2338706, "tid": 2379422, "ts": 6413850834447.861, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834448.811, "dur": 1.959, + "args": { + "External id": 1431488,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834449.190, "dur": 1.424, + "args": { + "External id": 1431489,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850834460.383, "dur": 398.391, + "args": { + "External id": 1431490,"Record function id": 0, "Sequence number": 15348729, "Fwd thread id": 1, "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850834461.706, "dur": 378.014, + "args": { + "External id": 1431491,"Sequence number": 15348729, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1474 + } + }, + { + "ph": "f", "id": 153, "pid": 2338706, "tid": 2379422, "ts": 6413850834461.706, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850834479.407, "dur": 7.368, + "args": { + "External id": 1431492,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834482.158, "dur": 4.010, + "args": { + "External id": 1431493,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850834488.985, "dur": 8.105, + "args": { + "External id": 1431494,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834492.445, "dur": 4.355, + "args": { + "External id": 1431495,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850834498.616, "dur": 3.032, + "args": { + "External id": 1431496,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834499.461, "dur": 1.910, + "args": { + "External id": 1431497,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850834533.686, "dur": 276.189, + "args": { + "External id": 1431498,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850834631.437, "dur": 6.320, + "args": { + "External id": 1431499,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850834639.864, "dur": 2.733, + "args": { + "External id": 1431500,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850834643.693, "dur": 4.531, + "args": { + "External id": 1431501,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850834649.388, "dur": 2.103, + "args": { + "External id": 1431502,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834698.538, "dur": 4.932, + "args": { + "External id": 1431503,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834701.750, "dur": 1.583, + "args": { + "External id": 1431504,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850834705.102, "dur": 29.605, + "args": { + "External id": 1431505,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834711.704, "dur": 0.815, + "args": { + "External id": 1431506,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850834738.476, "dur": 1.544, + "args": { + "External id": 1431507,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850834739.232, "dur": 0.688, + "args": { + "External id": 1431508,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850834740.945, "dur": 17.981, + "args": { + "External id": 1431509,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834742.453, "dur": 3.344, + "args": { + "External id": 1431510,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850834824.733, "dur": 4.143, + "args": { + "External id": 1431511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850834832.575, "dur": 0.740, + "args": { + "External id": 1431512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413850834835.631, "dur": 0.969, + "args": { + "External id": 1431513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850834867.492, "dur": 338.200, + "args": { + "External id": 1431514,"Record function id": 0, "Sequence number": 15348728, "Fwd thread id": 1, "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850834869.247, "dur": 325.083, + "args": { + "External id": 1431515,"Sequence number": 15348728, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1498 + } + }, + { + "ph": "f", "id": 154, "pid": 2338706, "tid": 2379422, "ts": 6413850834869.247, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850834892.373, "dur": 47.963, + "args": { + "External id": 1431516,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834898.440, "dur": 3.550, + "args": { + "External id": 1431517,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850834903.657, "dur": 35.822, + "args": { + "External id": 1431518,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 1501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850834952.484, "dur": 5.583, + "args": { + "External id": 1431519,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 1502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850834954.425, "dur": 3.295, + "args": { + "External id": 1431520,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850835217.630, "dur": 206.585, + "args": { + "External id": 1431521,"Record function id": 0, "Sequence number": 15348727, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850835220.292, "dur": 196.482, + "args": { + "External id": 1431522,"Sequence number": 15348727, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1505 + } + }, + { + "ph": "f", "id": 155, "pid": 2338706, "tid": 2379422, "ts": 6413850835220.292, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413850835240.498, "dur": 52.734, + "args": { + "External id": 1431523,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835245.795, "dur": 4.648, + "args": { + "External id": 1431524,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850835251.736, "dur": 40.602, + "args": { + "External id": 1431525,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 1508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413850835302.368, "dur": 6.383, + "args": { + "External id": 1431526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835303.928, "dur": 4.466, + "args": { + "External id": 1431527,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835431.860, "dur": 20.774, + "args": { + "External id": 1431528,"Record function id": 0, "Sequence number": 15348726, "Fwd thread id": 1, "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835433.341, "dur": 16.626, + "args": { + "External id": 1431529,"Sequence number": 15348726, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1512 + } + }, + { + "ph": "f", "id": 156, "pid": 2338706, "tid": 2379422, "ts": 6413850835433.341, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850835436.167, "dur": 13.437, + "args": { + "External id": 1431530,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850835440.198, "dur": 9.041, + "args": { + "External id": 1431531,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835459.203, "dur": 6.082, + "args": { + "External id": 1431532,"Record function id": 0, "Sequence number": 15348725, "Fwd thread id": 1, "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835460.087, "dur": 3.430, + "args": { + "External id": 1431533,"Sequence number": 15348725, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 1516 + } + }, + { + "ph": "f", "id": 157, "pid": 2338706, "tid": 2379422, "ts": 6413850835460.087, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850835461.492, "dur": 1.840, + "args": { + "External id": 1431534,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850835462.118, "dur": 1.058, + "args": { + "External id": 1431535,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 1518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835468.952, "dur": 8.857, + "args": { + "External id": 1431536,"Record function id": 0, "Sequence number": 15348724, "Fwd thread id": 1, "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835469.688, "dur": 5.648, + "args": { + "External id": 1431537,"Sequence number": 15348724, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 1520 + } + }, + { + "ph": "f", "id": 158, "pid": 2338706, "tid": 2379422, "ts": 6413850835469.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850835470.803, "dur": 4.366, + "args": { + "External id": 1431538,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850835474.072, "dur": 0.985, + "args": { + "External id": 1431539,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835481.653, "dur": 8.931, + "args": { + "External id": 1431540,"Record function id": 0, "Sequence number": 15348723, "Fwd thread id": 1, "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835482.553, "dur": 5.784, + "args": { + "External id": 1431541,"Sequence number": 15348723, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1524 + } + }, + { + "ph": "f", "id": 159, "pid": 2338706, "tid": 2379422, "ts": 6413850835482.553, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850835483.519, "dur": 4.615, + "args": { + "External id": 1431542,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850835486.808, "dur": 1.196, + "args": { + "External id": 1431543,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835494.525, "dur": 287.190, + "args": { + "External id": 1431544,"Record function id": 0, "Sequence number": 15348722, "Fwd thread id": 1, "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835495.575, "dur": 277.821, + "args": { + "External id": 1431545,"Sequence number": 15348722, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1528 + } + }, + { + "ph": "f", "id": 160, "pid": 2338706, "tid": 2379422, "ts": 6413850835495.575, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835500.115, "dur": 7.234, + "args": { + "External id": 1431546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835502.451, "dur": 4.112, + "args": { + "External id": 1431547,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835504.642, "dur": 1.576, + "args": { + "External id": 1431548,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850835511.568, "dur": 85.445, + "args": { + "External id": 1431549,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835598.576, "dur": 8.134, + "args": { + "External id": 1431550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835599.632, "dur": 6.172, + "args": { + "External id": 1431551,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835603.959, "dur": 1.671, + "args": { + "External id": 1431552,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835705.683, "dur": 6.283, + "args": { + "External id": 1431553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835707.427, "dur": 3.867, + "args": { + "External id": 1431554,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835710.743, "dur": 0.470, + "args": { + "External id": 1431555,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850835712.856, "dur": 59.255, + "args": { + "External id": 1431556,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835788.617, "dur": 10.221, + "args": { + "External id": 1431557,"Record function id": 0, "Sequence number": 15348721, "Fwd thread id": 1, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835789.791, "dur": 7.084, + "args": { + "External id": 1431558,"Sequence number": 15348721, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1541 + } + }, + { + "ph": "f", "id": 161, "pid": 2338706, "tid": 2379422, "ts": 6413850835789.791, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850835791.584, "dur": 5.116, + "args": { + "External id": 1431559,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850835794.884, "dur": 1.674, + "args": { + "External id": 1431560,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835802.636, "dur": 9.652, + "args": { + "External id": 1431561,"Record function id": 0, "Sequence number": 15348720, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835803.483, "dur": 6.875, + "args": { + "External id": 1431562,"Sequence number": 15348720, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1545 + } + }, + { + "ph": "f", "id": 162, "pid": 2338706, "tid": 2379422, "ts": 6413850835803.483, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835804.451, "dur": 5.643, + "args": { + "External id": 1431563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835807.628, "dur": 1.864, + "args": { + "External id": 1431564,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835808.630, "dur": 0.738, + "args": { + "External id": 1431565,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850835819.187, "dur": 10.475, + "args": { + "External id": 1431566,"Record function id": 0, "Ev Idx": 1549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850835820.963, "dur": 7.872, + "args": { + "External id": 1431567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850835823.951, "dur": 4.407, + "args": { + "External id": 1431568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850835825.153, "dur": 3.060, + "args": { + "External id": 1431569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835833.413, "dur": 9.055, + "args": { + "External id": 1431570,"Record function id": 0, "Sequence number": 15348719, "Fwd thread id": 1, "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835834.575, "dur": 5.661, + "args": { + "External id": 1431571,"Sequence number": 15348719, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 1554 + } + }, + { + "ph": "f", "id": 163, "pid": 2338706, "tid": 2379422, "ts": 6413850835834.575, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850835838.553, "dur": 1.482, + "args": { + "External id": 1431572,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850835839.029, "dur": 0.886, + "args": { + "External id": 1431573,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 1556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835845.890, "dur": 122.373, + "args": { + "External id": 1431574,"Record function id": 0, "Sequence number": 15348718, "Fwd thread id": 1, "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835849.045, "dur": 110.957, + "args": { + "External id": 1431575,"Sequence number": 15348718, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1558 + } + }, + { + "ph": "f", "id": 164, "pid": 2338706, "tid": 2379422, "ts": 6413850835849.045, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835851.093, "dur": 12.807, + "args": { + "External id": 1431576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 1559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835851.636, "dur": 11.638, + "args": { + "External id": 1431577,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 1560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835862.349, "dur": 0.620, + "args": { + "External id": 1431578,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850835864.949, "dur": 34.644, + "args": { + "External id": 1431579,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 1562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835900.998, "dur": 8.681, + "args": { + "External id": 1431580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835901.569, "dur": 7.415, + "args": { + "External id": 1431581,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 1564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835905.616, "dur": 3.053, + "args": { + "External id": 1431582,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 1565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850835911.288, "dur": 7.941, + "args": { + "External id": 1431583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850835912.144, "dur": 6.618, + "args": { + "External id": 1431584,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850835915.499, "dur": 3.144, + "args": { + "External id": 1431585,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850835919.723, "dur": 39.279, + "args": { + "External id": 1431586,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 1569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835997.152, "dur": 45.936, + "args": { + "External id": 1431587,"Record function id": 0, "Sequence number": 15348717, "Fwd thread id": 1, "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850835999.875, "dur": 4.951, + "args": { + "External id": 1431588,"Sequence number": 15348717, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1571 + } + }, + { + "ph": "f", "id": 165, "pid": 2338706, "tid": 2379422, "ts": 6413850835999.875, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850836001.701, "dur": 2.935, + "args": { + "External id": 1431589,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836002.333, "dur": 2.015, + "args": { + "External id": 1431590,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413850836009.090, "dur": 30.292, + "args": { + "External id": 1431591,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836052.604, "dur": 54.237, + "args": { + "External id": 1431592,"Record function id": 0, "Sequence number": 15348716, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836053.682, "dur": 49.548, + "args": { + "External id": 1431593,"Sequence number": 15348716, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1576 + } + }, + { + "ph": "f", "id": 166, "pid": 2338706, "tid": 2379422, "ts": 6413850836053.682, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850836093.229, "dur": 9.741, + "args": { + "External id": 1431594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 1577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850836095.792, "dur": 6.123, + "args": { + "External id": 1431595,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 1578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836100.424, "dur": 1.117, + "args": { + "External id": 1431596,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 1579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850836114.369, "dur": 7.556, + "args": { + "External id": 1431597,"Record function id": 0, "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850836115.961, "dur": 5.330, + "args": { + "External id": 1431598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850836117.925, "dur": 2.976, + "args": { + "External id": 1431599,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850836118.545, "dur": 2.224, + "args": { + "External id": 1431600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836125.541, "dur": 7.399, + "args": { + "External id": 1431601,"Record function id": 0, "Sequence number": 15348715, "Fwd thread id": 1, "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836127.136, "dur": 3.442, + "args": { + "External id": 1431602,"Sequence number": 15348715, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1585 + } + }, + { + "ph": "f", "id": 167, "pid": 2338706, "tid": 2379422, "ts": 6413850836127.136, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850836128.283, "dur": 2.111, + "args": { + "External id": 1431603,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836128.897, "dur": 1.369, + "args": { + "External id": 1431604,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836136.762, "dur": 126.978, + "args": { + "External id": 1431605,"Record function id": 0, "Sequence number": 15348714, "Fwd thread id": 1, "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836140.718, "dur": 113.850, + "args": { + "External id": 1431606,"Sequence number": 15348714, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1589 + } + }, + { + "ph": "f", "id": 168, "pid": 2338706, "tid": 2379422, "ts": 6413850836140.718, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850836143.484, "dur": 3.110, + "args": { + "External id": 1431607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850836144.151, "dur": 1.864, + "args": { + "External id": 1431608,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 1591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836145.246, "dur": 0.638, + "args": { + "External id": 1431609,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 1592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850836147.596, "dur": 52.634, + "args": { + "External id": 1431610,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850836201.526, "dur": 9.131, + "args": { + "External id": 1431611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850836202.392, "dur": 7.581, + "args": { + "External id": 1431612,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836208.327, "dur": 1.499, + "args": { + "External id": 1431613,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850836212.105, "dur": 3.108, + "args": { + "External id": 1431614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850836213.018, "dur": 1.717, + "args": { + "External id": 1431615,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836213.975, "dur": 0.625, + "args": { + "External id": 1431616,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850836215.685, "dur": 38.144, + "args": { + "External id": 1431617,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836269.473, "dur": 36.420, + "args": { + "External id": 1431618,"Record function id": 0, "Sequence number": 15348713, "Fwd thread id": 1, "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836270.375, "dur": 9.091, + "args": { + "External id": 1431619,"Sequence number": 15348713, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 1602 + } + }, + { + "ph": "f", "id": 169, "pid": 2338706, "tid": 2379422, "ts": 6413850836270.375, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850836274.126, "dur": 5.158, + "args": { + "External id": 1431620,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836277.569, "dur": 1.532, + "args": { + "External id": 1431621,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850836282.453, "dur": 20.402, + "args": { + "External id": 1431622,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836310.120, "dur": 8.847, + "args": { + "External id": 1431623,"Record function id": 0, "Sequence number": 15348712, "Fwd thread id": 1, "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413850836311.113, "dur": 5.182, + "args": { + "External id": 1431624,"Sequence number": 15348712, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1607 + } + }, + { + "ph": "f", "id": 170, "pid": 2338706, "tid": 2379422, "ts": 6413850836311.113, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413850836312.369, "dur": 3.704, + "args": { + "External id": 1431625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 1608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413850836313.435, "dur": 2.035, + "args": { + "External id": 1431626,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 1609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836314.699, "dur": 0.645, + "args": { + "External id": 1431627,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 1610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850836323.603, "dur": 6.171, + "args": { + "External id": 1431628,"Record function id": 0, "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850836325.359, "dur": 3.860, + "args": { + "External id": 1431629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850836326.511, "dur": 2.129, + "args": { + "External id": 1431630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850836327.239, "dur": 1.267, + "args": { + "External id": 1431631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850836334.764, "dur": 426.312, + "args": { + "External id": 1431632,"Record function id": 0, "Sequence number": 15348711, "Fwd thread id": 1, "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850836336.067, "dur": 390.203, + "args": { + "External id": 1431633,"Sequence number": 15348711, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1616 + } + }, + { + "ph": "f", "id": 171, "pid": 2338706, "tid": 2379422, "ts": 6413850836336.067, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850836386.040, "dur": 2.034, + "args": { + "External id": 1431634,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836386.633, "dur": 1.251, + "args": { + "External id": 1431635,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 1618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850836405.703, "dur": 7.647, + "args": { + "External id": 1431636,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850836425.790, "dur": 2.535, + "args": { + "External id": 1431637,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836604.669, "dur": 2.216, + "args": { + "External id": 1431638,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 1621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850836611.651, "dur": 41.947, + "args": { + "External id": 1431639,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 1622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836626.815, "dur": 0.826, + "args": { + "External id": 1431640,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 1623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850836660.161, "dur": 34.944, + "args": { + "External id": 1431641,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 1624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850836664.869, "dur": 29.979, + "args": { + "External id": 1431642,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 1625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850836669.251, "dur": 4.500, + "args": { + "External id": 1431643,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850836675.867, "dur": 18.234, + "args": { + "External id": 1431644,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 1627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413850836700.615, "dur": 2.496, + "args": { + "External id": 1431645,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 1628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836701.790, "dur": 1.148, + "args": { + "External id": 1431646,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 1629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850836713.390, "dur": 4.408, + "args": { + "External id": 1431647,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850836716.596, "dur": 1.078, + "args": { + "External id": 1431648,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 1631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413850836738.583, "dur": 17.423, + "args": { + "External id": 1431649,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 1632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850836771.578, "dur": 8.514, + "args": { + "External id": 1431650,"Record function id": 0, "Ev Idx": 1633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850836773.770, "dur": 5.511, + "args": { + "External id": 1431651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850836775.478, "dur": 2.780, + "args": { + "External id": 1431652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850836776.449, "dur": 1.670, + "args": { + "External id": 1431653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850836784.590, "dur": 3453.175, + "args": { + "External id": 1431654,"Record function id": 0, "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413850836818.799, "dur": 1112.148, + "args": { + "External id": 1431655,"Record function id": 0, "Ev Idx": 1638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 2338706, "tid": 2379422, + "ts": 6413850836847.997, "dur": 1071.439, + "args": { + "External id": 1431656,"Record function id": 0, "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413850836864.024, "dur": 1033.926, + "args": { + "External id": 1431657,"Record function id": 0, "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850836949.383, "dur": 7.929, + "args": { + "External id": 1431658,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413850836995.423, "dur": 47.512, + "args": { + "External id": 1431659,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837005.021, "dur": 2.052, + "args": { + "External id": 1431660,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837009.330, "dur": 3.461, + "args": { + "External id": 1431661,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837015.934, "dur": 0.605, + "args": { + "External id": 1431662,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837020.135, "dur": 0.403, + "args": { + "External id": 1431663,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837021.343, "dur": 1.099, + "args": { + "External id": 1431664,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837028.139, "dur": 0.580, + "args": { + "External id": 1431665,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837029.525, "dur": 0.454, + "args": { + "External id": 1431666,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837030.741, "dur": 2.372, + "args": { + "External id": 1431667,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837036.296, "dur": 0.463, + "args": { + "External id": 1431668,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850837095.146, "dur": 55.268, + "args": { + "External id": 1431669,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413850837199.497, "dur": 154.455, + "args": { + "External id": 1431670,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 1653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850837213.361, "dur": 9.169, + "args": { + "External id": 1431671,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413850837231.930, "dur": 13.794, + "args": { + "External id": 1431672,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413850837236.768, "dur": 8.468, + "args": { + "External id": 1431673,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 1656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837242.940, "dur": 0.579, + "args": { + "External id": 1431674,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413850837254.963, "dur": 34.704, + "args": { + "External id": 1431675,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837256.581, "dur": 0.487, + "args": { + "External id": 1431676,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837260.488, "dur": 2.597, + "args": { + "External id": 1431677,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837264.087, "dur": 0.307, + "args": { + "External id": 1431678,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837267.713, "dur": 1.080, + "args": { + "External id": 1431679,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837272.092, "dur": 0.461, + "args": { + "External id": 1431680,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837273.364, "dur": 0.255, + "args": { + "External id": 1431681,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837277.482, "dur": 2.706, + "args": { + "External id": 1431682,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837281.901, "dur": 0.419, + "args": { + "External id": 1431683,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850837283.242, "dur": 0.336, + "args": { + "External id": 1431684,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850837305.575, "dur": 38.135, + "args": { + "External id": 1431685,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413850837424.857, "dur": 344.504, + "args": { + "External id": 1431686,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 1669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413850837463.545, "dur": 298.589, + "args": { + "External id": 1431687,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1670, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413850837475.455, "dur": 278.757, + "args": { + "External id": 1431688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413850837799.106, "dur": 2.750, + "args": { + "External id": 1431689,"Record function id": 0, "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": 1672, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850837940.664, "dur": 2272.999, + "args": { + "External id": 1431690,"Sequence number": 15348710, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1673 + } + }, + { + "ph": "f", "id": 172, "pid": 2338706, "tid": 2379422, "ts": 6413850837940.664, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838171.729, "dur": 137.386, + "args": { + "External id": 1431691,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 1674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413850838374.272, "dur": 53.552, + "args": { + "External id": 1431692,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838454.287, "dur": 61.149, + "args": { + "External id": 1431693,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 1676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838527.626, "dur": 37.761, + "args": { + "External id": 1431694,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838572.321, "dur": 41.155, + "args": { + "External id": 1431695,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838624.216, "dur": 35.397, + "args": { + "External id": 1431696,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838668.512, "dur": 34.335, + "args": { + "External id": 1431697,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413850838737.818, "dur": 29.749, + "args": { + "External id": 1431698,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 1681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413850838791.638, "dur": 39.061, + "args": { + "External id": 1431699,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413850838865.260, "dur": 23.838, + "args": { + "External id": 1431700,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413850838908.683, "dur": 19.803, + "args": { + "External id": 1431701,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850838943.442, "dur": 64.661, + "args": { + "External id": 1431702,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839015.829, "dur": 86.529, + "args": { + "External id": 1431703,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413850839145.217, "dur": 308.380, + "args": { + "External id": 1431704,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850839240.706, "dur": 12.733, + "args": { + "External id": 1431705,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850839256.554, "dur": 7.259, + "args": { + "External id": 1431706,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850839265.272, "dur": 2.308, + "args": { + "External id": 1431707,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850839268.717, "dur": 2.289, + "args": { + "External id": 1431708,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850839325.190, "dur": 9.268, + "args": { + "External id": 1431709,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850839330.726, "dur": 3.471, + "args": { + "External id": 1431710,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850839337.109, "dur": 38.277, + "args": { + "External id": 1431711,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850839343.557, "dur": 1.933, + "args": { + "External id": 1431712,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413850839376.964, "dur": 4.351, + "args": { + "External id": 1431713,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850839380.507, "dur": 0.686, + "args": { + "External id": 1431714,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413850839382.607, "dur": 21.807, + "args": { + "External id": 1431715,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850839386.610, "dur": 2.800, + "args": { + "External id": 1431716,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413850839503.258, "dur": 37.496, + "args": { + "External id": 1431717,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413850839562.412, "dur": 21.412, + "args": { + "External id": 1431718,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839591.907, "dur": 55.120, + "args": { + "External id": 1431719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839657.402, "dur": 44.011, + "args": { + "External id": 1431720,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839709.996, "dur": 25.407, + "args": { + "External id": 1431721,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839742.210, "dur": 36.713, + "args": { + "External id": 1431722,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839787.169, "dur": 30.909, + "args": { + "External id": 1431723,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413850839827.178, "dur": 35.902, + "args": { + "External id": 1431724,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413850839888.383, "dur": 29.856, + "args": { + "External id": 1431725,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 1708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413850839941.759, "dur": 32.117, + "args": { + "External id": 1431726,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413850840016.734, "dur": 24.130, + "args": { + "External id": 1431727,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413850840103.004, "dur": 25.408, + "args": { + "External id": 1431728,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413850840150.858, "dur": 25.396, + "args": { + "External id": 1431729,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 1712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840265.398, "dur": 21.290, + "args": { + "External id": 1431730,"Record function id": 0, "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840269.351, "dur": 16.157, + "args": { + "External id": 1431731,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840274.551, "dur": 9.803, + "args": { + "External id": 1431732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840276.821, "dur": 7.402, + "args": { + "External id": 1431733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840291.444, "dur": 5.589, + "args": { + "External id": 1431734,"Record function id": 0, "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840293.020, "dur": 3.474, + "args": { + "External id": 1431735,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840293.877, "dur": 2.029, + "args": { + "External id": 1431736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840294.528, "dur": 1.250, + "args": { + "External id": 1431737,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840300.993, "dur": 5.515, + "args": { + "External id": 1431738,"Record function id": 0, "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840302.403, "dur": 3.594, + "args": { + "External id": 1431739,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840303.283, "dur": 2.220, + "args": { + "External id": 1431740,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840304.408, "dur": 0.984, + "args": { + "External id": 1431741,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840310.541, "dur": 4.932, + "args": { + "External id": 1431742,"Record function id": 0, "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840312.023, "dur": 2.945, + "args": { + "External id": 1431743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840312.973, "dur": 1.483, + "args": { + "External id": 1431744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840313.594, "dur": 0.764, + "args": { + "External id": 1431745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840319.094, "dur": 29.071, + "args": { + "External id": 1431746,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840320.399, "dur": 27.007, + "args": { + "External id": 1431747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840343.751, "dur": 3.081, + "args": { + "External id": 1431748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840344.802, "dur": 1.929, + "args": { + "External id": 1431749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840352.358, "dur": 9.839, + "args": { + "External id": 1431750,"Record function id": 0, "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840356.338, "dur": 5.308, + "args": { + "External id": 1431751,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840356.958, "dur": 4.157, + "args": { + "External id": 1431752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840360.214, "dur": 0.780, + "args": { + "External id": 1431753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840368.042, "dur": 4.327, + "args": { + "External id": 1431754,"Record function id": 0, "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840369.426, "dur": 2.437, + "args": { + "External id": 1431755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840370.199, "dur": 1.191, + "args": { + "External id": 1431756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840370.577, "dur": 0.733, + "args": { + "External id": 1431757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840376.428, "dur": 6.316, + "args": { + "External id": 1431758,"Record function id": 0, "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840377.514, "dur": 4.755, + "args": { + "External id": 1431759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840378.069, "dur": 3.714, + "args": { + "External id": 1431760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840378.418, "dur": 3.280, + "args": { + "External id": 1431761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840386.599, "dur": 4.595, + "args": { + "External id": 1431762,"Record function id": 0, "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413850840387.783, "dur": 2.884, + "args": { + "External id": 1431763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840388.536, "dur": 1.658, + "args": { + "External id": 1431764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413850840389.207, "dur": 0.912, + "args": { + "External id": 1431765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850840396.235, "dur": 279042.156, + "args": { + "External id": 1431766,"Record function id": 0, "Sequence number": 15348709, "Fwd thread id": 1, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413850840397.728, "dur": 279028.798, + "args": { + "External id": 1431767,"Sequence number": 15348709, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1750 + } + }, + { + "ph": "f", "id": 173, "pid": 2338706, "tid": 2379422, "ts": 6413850840397.728, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413850840433.922, "dur": 48.730, + "args": { + "External id": 1431768,"Record function id": 0, "Ev Idx": 1751 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413850840494.148, "dur": 81.589, + "args": { + "External id": 1431769,"Record function id": 0, "Ev Idx": 1752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413850840582.934, "dur": 278831.972, + "args": { + "External id": 1431770,"Record function id": 0, "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850840646.127, "dur": 10.313, + "args": { + "External id": 1431771,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413850840668.130, "dur": 5.419, + "args": { + "External id": 1431772,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413850840693.111, "dur": 277581.719, + "args": { + "External id": 1431773,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413850840708.578, "dur": 277544.605, + "args": { + "External id": 1431774,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413850840902.915, "dur": 6.712, + "args": { + "External id": 1431775,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413850840954.020, "dur": 277231.357, + "args": { + "External id": 1431776,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 1759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413850840958.330, "dur": 277225.251, + "args": { + "External id": 1431777,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 1760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413850840962.460, "dur": 38.210, + "args": { + "External id": 1431778,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413850841005.577, "dur": 277166.100, + "args": { + "External id": 1431779,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 1762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851118444.468, "dur": 24.171, + "args": { + "External id": 1431780,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 1763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851118455.184, "dur": 12.980, + "args": { + "External id": 1431781,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851118519.561, "dur": 434.736, + "args": { + "External id": 1431782,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 1765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851118566.387, "dur": 382.013, + "args": { + "External id": 1431783,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1766, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851118580.667, "dur": 361.246, + "args": { + "External id": 1431784,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 1767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851118997.406, "dur": 3.400, + "args": { + "External id": 1431785,"Record function id": 0, "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": 1768, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119113.385, "dur": 8.425, + "args": { + "External id": 1431786,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119198.924, "dur": 2.184, + "args": { + "External id": 1431787,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119222.486, "dur": 1.784, + "args": { + "External id": 1431788,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119243.768, "dur": 1.610, + "args": { + "External id": 1431789,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119260.038, "dur": 1.637, + "args": { + "External id": 1431790,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119277.598, "dur": 1.494, + "args": { + "External id": 1431791,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119290.742, "dur": 1.530, + "args": { + "External id": 1431792,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119307.920, "dur": 4.036, + "args": { + "External id": 1431793,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119326.156, "dur": 1.044, + "args": { + "External id": 1431794,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851119458.543, "dur": 3403.101, + "args": { + "External id": 1431795,"Record function id": 0, "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413851119487.714, "dur": 1315.445, + "args": { + "External id": 1431796,"Record function id": 0, "Ev Idx": 1779 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413851119507.855, "dur": 401.485, + "args": { + "External id": 1431797,"Record function id": 0, "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119623.435, "dur": 4.580, + "args": { + "External id": 1431798,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119631.158, "dur": 1.318, + "args": { + "External id": 1431799,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119634.116, "dur": 1.420, + "args": { + "External id": 1431800,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119637.316, "dur": 1.214, + "args": { + "External id": 1431801,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119639.940, "dur": 1.099, + "args": { + "External id": 1431802,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119645.045, "dur": 0.965, + "args": { + "External id": 1431803,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119649.818, "dur": 3.669, + "args": { + "External id": 1431804,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119655.083, "dur": 3.427, + "args": { + "External id": 1431805,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119660.043, "dur": 1.361, + "args": { + "External id": 1431806,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851119665.756, "dur": 1.108, + "args": { + "External id": 1431807,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851119690.288, "dur": 187.275, + "args": { + "External id": 1431808,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851119712.121, "dur": 160.393, + "args": { + "External id": 1431809,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851119735.978, "dur": 15.736, + "args": { + "External id": 1431810,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851119757.970, "dur": 80.648, + "args": { + "External id": 1431811,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 1794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851119761.406, "dur": 76.857, + "args": { + "External id": 1431812,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 1795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851119767.853, "dur": 7.979, + "args": { + "External id": 1431813,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851119778.160, "dur": 59.612, + "args": { + "External id": 1431814,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 1797 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.23", "pid": 2338706, "tid": 2379422, + "ts": 6413851120041.013, "dur": 753.900, + "args": { + "External id": 1431815,"Record function id": 0, "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413851120099.041, "dur": 680.648, + "args": { + "External id": 1431816,"Record function id": 0, "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851120174.634, "dur": 7.002, + "args": { + "External id": 1431817,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851120202.392, "dur": 44.336, + "args": { + "External id": 1431818,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120210.226, "dur": 2.057, + "args": { + "External id": 1431819,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120213.848, "dur": 2.818, + "args": { + "External id": 1431820,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120217.766, "dur": 3.103, + "args": { + "External id": 1431821,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120223.325, "dur": 0.603, + "args": { + "External id": 1431822,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120226.763, "dur": 0.586, + "args": { + "External id": 1431823,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120230.166, "dur": 0.535, + "args": { + "External id": 1431824,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120231.792, "dur": 0.480, + "args": { + "External id": 1431825,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120235.256, "dur": 0.373, + "args": { + "External id": 1431826,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120239.243, "dur": 0.562, + "args": { + "External id": 1431827,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851120258.801, "dur": 49.613, + "args": { + "External id": 1431828,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851120345.716, "dur": 166.308, + "args": { + "External id": 1431829,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851120356.736, "dur": 3.620, + "args": { + "External id": 1431830,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851120367.182, "dur": 42.514, + "args": { + "External id": 1431831,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851120398.055, "dur": 11.029, + "args": { + "External id": 1431832,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 1815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120404.358, "dur": 3.125, + "args": { + "External id": 1431833,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851120417.813, "dur": 35.459, + "args": { + "External id": 1431834,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120419.703, "dur": 0.668, + "args": { + "External id": 1431835,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120425.569, "dur": 0.554, + "args": { + "External id": 1431836,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120427.080, "dur": 0.469, + "args": { + "External id": 1431837,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120430.061, "dur": 2.449, + "args": { + "External id": 1431838,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120433.827, "dur": 0.449, + "args": { + "External id": 1431839,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120434.834, "dur": 0.729, + "args": { + "External id": 1431840,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120441.496, "dur": 0.354, + "args": { + "External id": 1431841,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120442.428, "dur": 2.247, + "args": { + "External id": 1431842,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851120445.601, "dur": 0.362, + "args": { + "External id": 1431843,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851120469.281, "dur": 34.182, + "args": { + "External id": 1431844,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851120563.594, "dur": 140.811, + "args": { + "External id": 1431845,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851120600.870, "dur": 100.140, + "args": { + "External id": 1431846,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1829, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851120610.759, "dur": 85.621, + "args": { + "External id": 1431847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 1830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851120723.272, "dur": 1.777, + "args": { + "External id": 1431848,"Record function id": 0, "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": 1831, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851120811.290, "dur": 2017.783, + "args": { + "External id": 1431849,"Sequence number": 15348708, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1832 + } + }, + { + "ph": "f", "id": 174, "pid": 2338706, "tid": 2379422, "ts": 6413851120811.290, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851120957.365, "dur": 182.721, + "args": { + "External id": 1431850,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 1833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851121198.149, "dur": 54.016, + "args": { + "External id": 1431851,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 1834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121276.862, "dur": 58.567, + "args": { + "External id": 1431852,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 1835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121347.391, "dur": 34.018, + "args": { + "External id": 1431853,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121391.465, "dur": 35.495, + "args": { + "External id": 1431854,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121435.364, "dur": 27.388, + "args": { + "External id": 1431855,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121473.050, "dur": 28.923, + "args": { + "External id": 1431856,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851121531.405, "dur": 27.499, + "args": { + "External id": 1431857,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851121583.400, "dur": 36.485, + "args": { + "External id": 1431858,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851121647.496, "dur": 23.480, + "args": { + "External id": 1431859,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851121692.381, "dur": 18.724, + "args": { + "External id": 1431860,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121721.493, "dur": 35.424, + "args": { + "External id": 1431861,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851121760.723, "dur": 32.462, + "args": { + "External id": 1431862,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851121827.711, "dur": 389.936, + "args": { + "External id": 1431863,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851121931.546, "dur": 6.382, + "args": { + "External id": 1431864,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851121940.296, "dur": 2.398, + "args": { + "External id": 1431865,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851121943.824, "dur": 4.566, + "args": { + "External id": 1431866,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851121949.627, "dur": 5.696, + "args": { + "External id": 1431867,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851122036.017, "dur": 6.485, + "args": { + "External id": 1431868,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851122038.270, "dur": 3.546, + "args": { + "External id": 1431869,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851122047.148, "dur": 72.515, + "args": { + "External id": 1431870,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851122086.985, "dur": 3.789, + "args": { + "External id": 1431871,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851122121.563, "dur": 1.908, + "args": { + "External id": 1431872,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851122122.687, "dur": 0.715, + "args": { + "External id": 1431873,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 1856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851122124.650, "dur": 20.558, + "args": { + "External id": 1431874,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 1857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851122131.304, "dur": 0.739, + "args": { + "External id": 1431875,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 1858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851122268.086, "dur": 35.920, + "args": { + "External id": 1431876,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851122325.001, "dur": 18.313, + "args": { + "External id": 1431877,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851122351.325, "dur": 52.012, + "args": { + "External id": 1431878,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851122409.556, "dur": 39.735, + "args": { + "External id": 1431879,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851122459.734, "dur": 20.585, + "args": { + "External id": 1431880,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 1863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851122485.743, "dur": 30.253, + "args": { + "External id": 1431881,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 1864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851122523.507, "dur": 27.254, + "args": { + "External id": 1431882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 1865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851122557.505, "dur": 30.032, + "args": { + "External id": 1431883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 1866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851122610.828, "dur": 30.460, + "args": { + "External id": 1431884,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 1867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851122660.158, "dur": 28.498, + "args": { + "External id": 1431885,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851122707.712, "dur": 18.909, + "args": { + "External id": 1431886,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 1869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851122745.494, "dur": 15.496, + "args": { + "External id": 1431887,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 1870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851122777.715, "dur": 16.611, + "args": { + "External id": 1431888,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 1871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122884.698, "dur": 16.452, + "args": { + "External id": 1431889,"Record function id": 0, "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122888.332, "dur": 11.640, + "args": { + "External id": 1431890,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122893.095, "dur": 5.531, + "args": { + "External id": 1431891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122894.718, "dur": 3.793, + "args": { + "External id": 1431892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122905.445, "dur": 7.812, + "args": { + "External id": 1431893,"Record function id": 0, "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122906.948, "dur": 5.872, + "args": { + "External id": 1431894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122907.752, "dur": 4.607, + "args": { + "External id": 1431895,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122908.565, "dur": 3.713, + "args": { + "External id": 1431896,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122916.622, "dur": 5.172, + "args": { + "External id": 1431897,"Record function id": 0, "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122917.967, "dur": 3.390, + "args": { + "External id": 1431898,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122918.783, "dur": 2.104, + "args": { + "External id": 1431899,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122919.853, "dur": 0.937, + "args": { + "External id": 1431900,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 1883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122925.134, "dur": 4.124, + "args": { + "External id": 1431901,"Record function id": 0, "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122926.330, "dur": 2.521, + "args": { + "External id": 1431902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122927.339, "dur": 1.128, + "args": { + "External id": 1431903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122927.810, "dur": 0.577, + "args": { + "External id": 1431904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 1887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122932.802, "dur": 4.254, + "args": { + "External id": 1431905,"Record function id": 0, "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122934.032, "dur": 2.593, + "args": { + "External id": 1431906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122934.699, "dur": 1.206, + "args": { + "External id": 1431907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122935.152, "dur": 0.678, + "args": { + "External id": 1431908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122940.208, "dur": 4.177, + "args": { + "External id": 1431909,"Record function id": 0, "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122941.333, "dur": 2.618, + "args": { + "External id": 1431910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122942.131, "dur": 1.135, + "args": { + "External id": 1431911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122942.625, "dur": 0.567, + "args": { + "External id": 1431912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 1895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122947.706, "dur": 54.088, + "args": { + "External id": 1431913,"Record function id": 0, "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851122950.713, "dur": 49.906, + "args": { + "External id": 1431914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122951.518, "dur": 47.925, + "args": { + "External id": 1431915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851122997.238, "dur": 1.788, + "args": { + "External id": 1431916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851123007.610, "dur": 5.402, + "args": { + "External id": 1431917,"Record function id": 0, "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851123009.583, "dur": 2.992, + "args": { + "External id": 1431918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851123010.548, "dur": 1.494, + "args": { + "External id": 1431919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851123011.166, "dur": 0.800, + "args": { + "External id": 1431920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 1903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851123016.093, "dur": 7.017, + "args": { + "External id": 1431921,"Record function id": 0, "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851123017.342, "dur": 5.349, + "args": { + "External id": 1431922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851123017.808, "dur": 4.311, + "args": { + "External id": 1431923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851123018.595, "dur": 3.453, + "args": { + "External id": 1431924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 1907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851123027.759, "dur": 86153.631, + "args": { + "External id": 1431925,"Record function id": 0, "Sequence number": 15348707, "Fwd thread id": 1, "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851123029.442, "dur": 86142.065, + "args": { + "External id": 1431926,"Sequence number": 15348707, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1909 + } + }, + { + "ph": "f", "id": 175, "pid": 2338706, "tid": 2379422, "ts": 6413851123029.442, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413851123102.904, "dur": 44.627, + "args": { + "External id": 1431927,"Record function id": 0, "Ev Idx": 1910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413851123158.643, "dur": 80.270, + "args": { + "External id": 1431928,"Record function id": 0, "Ev Idx": 1911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413851123244.440, "dur": 85918.258, + "args": { + "External id": 1431929,"Record function id": 0, "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851123346.522, "dur": 8.625, + "args": { + "External id": 1431930,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851123365.950, "dur": 5.148, + "args": { + "External id": 1431931,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851123385.822, "dur": 84839.899, + "args": { + "External id": 1431932,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851123401.023, "dur": 84810.108, + "args": { + "External id": 1431933,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 1916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851123608.011, "dur": 19.129, + "args": { + "External id": 1431934,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851123683.496, "dur": 84479.971, + "args": { + "External id": 1431935,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 1918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851123686.418, "dur": 84475.945, + "args": { + "External id": 1431936,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 1919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851123690.732, "dur": 14.888, + "args": { + "External id": 1431937,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851123707.867, "dur": 84448.956, + "args": { + "External id": 1431938,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 1921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851208343.896, "dur": 12.655, + "args": { + "External id": 1431939,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 1922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851208347.763, "dur": 8.440, + "args": { + "External id": 1431940,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851208388.738, "dur": 395.705, + "args": { + "External id": 1431941,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 1924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851208426.235, "dur": 353.060, + "args": { + "External id": 1431942,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1925, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851208439.609, "dur": 334.423, + "args": { + "External id": 1431943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 1926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851208806.086, "dur": 2.231, + "args": { + "External id": 1431944,"Record function id": 0, "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": 1927, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851208864.632, "dur": 6.462, + "args": { + "External id": 1431945,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851208919.084, "dur": 3.803, + "args": { + "External id": 1431946,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851208939.930, "dur": 1.463, + "args": { + "External id": 1431947,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851208956.794, "dur": 1.177, + "args": { + "External id": 1431948,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851208994.259, "dur": 1.670, + "args": { + "External id": 1431949,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209012.282, "dur": 3.537, + "args": { + "External id": 1431950,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209028.912, "dur": 1.014, + "args": { + "External id": 1431951,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209040.349, "dur": 3.570, + "args": { + "External id": 1431952,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209087.068, "dur": 1.540, + "args": { + "External id": 1431953,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851209198.042, "dur": 3126.780, + "args": { + "External id": 1431954,"Record function id": 0, "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413851209221.395, "dur": 1229.620, + "args": { + "External id": 1431955,"Record function id": 0, "Ev Idx": 1938 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413851209237.080, "dur": 401.201, + "args": { + "External id": 1431956,"Record function id": 0, "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209331.718, "dur": 6.917, + "args": { + "External id": 1431957,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 1940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209341.821, "dur": 1.167, + "args": { + "External id": 1431958,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209344.861, "dur": 1.123, + "args": { + "External id": 1431959,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209347.791, "dur": 1.119, + "args": { + "External id": 1431960,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209353.033, "dur": 1.435, + "args": { + "External id": 1431961,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209355.981, "dur": 1.015, + "args": { + "External id": 1431962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 1945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209359.141, "dur": 3.061, + "args": { + "External id": 1431963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 1946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209363.631, "dur": 0.993, + "args": { + "External id": 1431964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209369.077, "dur": 3.396, + "args": { + "External id": 1431965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851209374.060, "dur": 1.034, + "args": { + "External id": 1431966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 1949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851209434.702, "dur": 169.728, + "args": { + "External id": 1431967,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851209453.786, "dur": 146.026, + "args": { + "External id": 1431968,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 1951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851209476.742, "dur": 15.814, + "args": { + "External id": 1431969,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851209498.026, "dur": 72.564, + "args": { + "External id": 1431970,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 1953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851209503.863, "dur": 66.416, + "args": { + "External id": 1431971,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 1954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209508.053, "dur": 7.525, + "args": { + "External id": 1431972,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851209517.335, "dur": 52.488, + "args": { + "External id": 1431973,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 1956 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.22", "pid": 2338706, "tid": 2379422, + "ts": 6413851209736.678, "dur": 706.026, + "args": { + "External id": 1431974,"Record function id": 0, "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413851209753.646, "dur": 674.922, + "args": { + "External id": 1431975,"Record function id": 0, "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851209822.926, "dur": 4.676, + "args": { + "External id": 1431976,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851209844.543, "dur": 42.884, + "args": { + "External id": 1431977,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209849.595, "dur": 1.462, + "args": { + "External id": 1431978,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209853.075, "dur": 2.615, + "args": { + "External id": 1431979,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209857.784, "dur": 0.511, + "args": { + "External id": 1431980,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209860.138, "dur": 2.807, + "args": { + "External id": 1431981,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209869.550, "dur": 0.426, + "args": { + "External id": 1431982,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209871.538, "dur": 0.567, + "args": { + "External id": 1431983,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209873.881, "dur": 0.599, + "args": { + "External id": 1431984,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209878.243, "dur": 0.335, + "args": { + "External id": 1431985,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851209880.033, "dur": 0.294, + "args": { + "External id": 1431986,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851209899.193, "dur": 41.802, + "args": { + "External id": 1431987,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851209992.802, "dur": 170.664, + "args": { + "External id": 1431988,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 1971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851210005.929, "dur": 4.998, + "args": { + "External id": 1431989,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851210016.765, "dur": 12.013, + "args": { + "External id": 1431990,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851210021.403, "dur": 6.918, + "args": { + "External id": 1431991,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 1974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210025.527, "dur": 1.172, + "args": { + "External id": 1431992,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 1975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851210036.672, "dur": 71.560, + "args": { + "External id": 1431993,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 1976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210038.881, "dur": 3.005, + "args": { + "External id": 1431994,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210045.385, "dur": 0.678, + "args": { + "External id": 1431995,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210047.556, "dur": 0.618, + "args": { + "External id": 1431996,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210049.930, "dur": 2.427, + "args": { + "External id": 1431997,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210087.186, "dur": 0.629, + "args": { + "External id": 1431998,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210089.804, "dur": 0.463, + "args": { + "External id": 1431999,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210093.677, "dur": 0.464, + "args": { + "External id": 1432000,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210096.041, "dur": 0.420, + "args": { + "External id": 1432001,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851210097.983, "dur": 2.630, + "args": { + "External id": 1432002,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851210121.964, "dur": 33.016, + "args": { + "External id": 1432003,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 1986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851210214.474, "dur": 137.570, + "args": { + "External id": 1432004,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 1987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851210249.027, "dur": 99.558, + "args": { + "External id": 1432005,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1988, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851210259.016, "dur": 84.853, + "args": { + "External id": 1432006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851210371.561, "dur": 2.051, + "args": { + "External id": 1432007,"Record function id": 0, "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": 1990, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851210459.418, "dur": 1837.993, + "args": { + "External id": 1432008,"Sequence number": 15348706, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 1991 + } + }, + { + "ph": "f", "id": 176, "pid": 2338706, "tid": 2379422, "ts": 6413851210459.418, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851210581.699, "dur": 111.213, + "args": { + "External id": 1432009,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 1992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851210736.634, "dur": 38.703, + "args": { + "External id": 1432010,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851210796.319, "dur": 47.071, + "args": { + "External id": 1432011,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 1994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851210853.730, "dur": 30.738, + "args": { + "External id": 1432012,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851210890.972, "dur": 30.883, + "args": { + "External id": 1432013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851210931.308, "dur": 26.752, + "args": { + "External id": 1432014,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851210968.262, "dur": 51.961, + "args": { + "External id": 1432015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 1998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851211049.357, "dur": 62.213, + "args": { + "External id": 1432016,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851211135.449, "dur": 29.607, + "args": { + "External id": 1432017,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851211192.464, "dur": 19.646, + "args": { + "External id": 1432018,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851211227.130, "dur": 16.159, + "args": { + "External id": 1432019,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211253.714, "dur": 39.570, + "args": { + "External id": 1432020,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211296.787, "dur": 32.384, + "args": { + "External id": 1432021,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851211361.289, "dur": 260.273, + "args": { + "External id": 1432022,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851211448.082, "dur": 8.725, + "args": { + "External id": 1432023,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851211459.051, "dur": 2.604, + "args": { + "External id": 1432024,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851211463.022, "dur": 1.743, + "args": { + "External id": 1432025,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851211466.020, "dur": 3.489, + "args": { + "External id": 1432026,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851211516.144, "dur": 5.107, + "args": { + "External id": 1432027,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851211518.086, "dur": 2.976, + "args": { + "External id": 1432028,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851211523.362, "dur": 32.732, + "args": { + "External id": 1432029,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851211528.600, "dur": 3.907, + "args": { + "External id": 1432030,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851211557.594, "dur": 2.434, + "args": { + "External id": 1432031,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851211559.139, "dur": 0.790, + "args": { + "External id": 1432032,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851211561.462, "dur": 14.399, + "args": { + "External id": 1432033,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851211564.291, "dur": 0.615, + "args": { + "External id": 1432034,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851211663.497, "dur": 26.069, + "args": { + "External id": 1432035,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851211709.083, "dur": 16.015, + "args": { + "External id": 1432036,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211732.116, "dur": 37.055, + "args": { + "External id": 1432037,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211775.316, "dur": 35.480, + "args": { + "External id": 1432038,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211820.725, "dur": 19.740, + "args": { + "External id": 1432039,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211845.716, "dur": 43.354, + "args": { + "External id": 1432040,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211904.587, "dur": 32.779, + "args": { + "External id": 1432041,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851211944.710, "dur": 48.888, + "args": { + "External id": 1432042,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851212021.798, "dur": 76.609, + "args": { + "External id": 1432043,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851212125.706, "dur": 28.840, + "args": { + "External id": 1432044,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851212173.472, "dur": 21.744, + "args": { + "External id": 1432045,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851212216.804, "dur": 13.170, + "args": { + "External id": 1432046,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851212250.776, "dur": 16.174, + "args": { + "External id": 1432047,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212347.930, "dur": 17.105, + "args": { + "External id": 1432048,"Record function id": 0, "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212352.388, "dur": 11.555, + "args": { + "External id": 1432049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212356.934, "dur": 5.912, + "args": { + "External id": 1432050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212358.619, "dur": 4.130, + "args": { + "External id": 1432051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212369.073, "dur": 5.656, + "args": { + "External id": 1432052,"Record function id": 0, "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212370.968, "dur": 3.315, + "args": { + "External id": 1432053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212371.949, "dur": 1.701, + "args": { + "External id": 1432054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212372.832, "dur": 0.707, + "args": { + "External id": 1432055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212378.285, "dur": 7.677, + "args": { + "External id": 1432056,"Record function id": 0, "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212379.915, "dur": 5.588, + "args": { + "External id": 1432057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212380.408, "dur": 4.370, + "args": { + "External id": 1432058,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212381.402, "dur": 3.250, + "args": { + "External id": 1432059,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212389.082, "dur": 5.582, + "args": { + "External id": 1432060,"Record function id": 0, "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212391.077, "dur": 3.129, + "args": { + "External id": 1432061,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212391.856, "dur": 1.917, + "args": { + "External id": 1432062,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212392.603, "dur": 1.064, + "args": { + "External id": 1432063,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212397.791, "dur": 107.371, + "args": { + "External id": 1432064,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212501.034, "dur": 3.538, + "args": { + "External id": 1432065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212502.810, "dur": 1.221, + "args": { + "External id": 1432066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212503.228, "dur": 0.678, + "args": { + "External id": 1432067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212508.915, "dur": 7.773, + "args": { + "External id": 1432068,"Record function id": 0, "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212511.245, "dur": 4.990, + "args": { + "External id": 1432069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212511.803, "dur": 3.896, + "args": { + "External id": 1432070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212514.889, "dur": 0.722, + "args": { + "External id": 1432071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212522.164, "dur": 4.060, + "args": { + "External id": 1432072,"Record function id": 0, "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212523.452, "dur": 2.362, + "args": { + "External id": 1432073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212524.092, "dur": 1.250, + "args": { + "External id": 1432074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212524.363, "dur": 0.893, + "args": { + "External id": 1432075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212529.649, "dur": 3.797, + "args": { + "External id": 1432076,"Record function id": 0, "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212530.670, "dur": 2.357, + "args": { + "External id": 1432077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212531.396, "dur": 0.900, + "args": { + "External id": 1432078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212531.680, "dur": 0.542, + "args": { + "External id": 1432079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212537.022, "dur": 3.601, + "args": { + "External id": 1432080,"Record function id": 0, "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851212538.132, "dur": 2.078, + "args": { + "External id": 1432081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212538.622, "dur": 1.141, + "args": { + "External id": 1432082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851212539.135, "dur": 0.560, + "args": { + "External id": 1432083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851212544.543, "dur": 73483.594, + "args": { + "External id": 1432084,"Record function id": 0, "Sequence number": 15348705, "Fwd thread id": 1, "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851212553.546, "dur": 73463.763, + "args": { + "External id": 1432085,"Sequence number": 15348705, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2068 + } + }, + { + "ph": "f", "id": 177, "pid": 2338706, "tid": 2379422, "ts": 6413851212553.546, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413851212588.396, "dur": 43.279, + "args": { + "External id": 1432086,"Record function id": 0, "Ev Idx": 2069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413851212639.712, "dur": 72.406, + "args": { + "External id": 1432087,"Record function id": 0, "Ev Idx": 2070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413851212718.035, "dur": 73289.788, + "args": { + "External id": 1432088,"Record function id": 0, "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851212812.344, "dur": 7.394, + "args": { + "External id": 1432089,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851212829.460, "dur": 6.906, + "args": { + "External id": 1432090,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851212853.451, "dur": 72173.776, + "args": { + "External id": 1432091,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851212867.062, "dur": 72145.781, + "args": { + "External id": 1432092,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851213132.051, "dur": 20.764, + "args": { + "External id": 1432093,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851213177.280, "dur": 71778.879, + "args": { + "External id": 1432094,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851213180.695, "dur": 71773.004, + "args": { + "External id": 1432095,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851213185.743, "dur": 14.169, + "args": { + "External id": 1432096,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851213201.778, "dur": 71746.728, + "args": { + "External id": 1432097,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851285168.454, "dur": 13.232, + "args": { + "External id": 1432098,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851285172.436, "dur": 8.641, + "args": { + "External id": 1432099,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851285214.508, "dur": 443.585, + "args": { + "External id": 1432100,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851285249.977, "dur": 402.751, + "args": { + "External id": 1432101,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2084, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851285263.441, "dur": 383.620, + "args": { + "External id": 1432102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851285683.984, "dur": 2.123, + "args": { + "External id": 1432103,"Record function id": 0, "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": 2086, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285750.134, "dur": 7.048, + "args": { + "External id": 1432104,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285806.625, "dur": 1.259, + "args": { + "External id": 1432105,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285827.160, "dur": 3.651, + "args": { + "External id": 1432106,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285845.167, "dur": 1.147, + "args": { + "External id": 1432107,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285860.565, "dur": 0.677, + "args": { + "External id": 1432108,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285874.430, "dur": 0.815, + "args": { + "External id": 1432109,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285888.022, "dur": 3.307, + "args": { + "External id": 1432110,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285903.613, "dur": 3.281, + "args": { + "External id": 1432111,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851285921.453, "dur": 1.268, + "args": { + "External id": 1432112,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851286045.807, "dur": 3090.792, + "args": { + "External id": 1432113,"Record function id": 0, "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413851286105.851, "dur": 1151.897, + "args": { + "External id": 1432114,"Record function id": 0, "Ev Idx": 2097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413851286122.398, "dur": 357.729, + "args": { + "External id": 1432115,"Record function id": 0, "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286221.302, "dur": 5.406, + "args": { + "External id": 1432116,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286230.298, "dur": 1.175, + "args": { + "External id": 1432117,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286233.237, "dur": 3.312, + "args": { + "External id": 1432118,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286238.574, "dur": 1.346, + "args": { + "External id": 1432119,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286241.577, "dur": 0.852, + "args": { + "External id": 1432120,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286243.828, "dur": 0.798, + "args": { + "External id": 1432121,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286246.161, "dur": 3.498, + "args": { + "External id": 1432122,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286253.549, "dur": 0.821, + "args": { + "External id": 1432123,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286256.056, "dur": 0.724, + "args": { + "External id": 1432124,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851286258.218, "dur": 0.985, + "args": { + "External id": 1432125,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851286277.587, "dur": 168.289, + "args": { + "External id": 1432126,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851286295.342, "dur": 145.159, + "args": { + "External id": 1432127,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851286322.936, "dur": 17.971, + "args": { + "External id": 1432128,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851286345.662, "dur": 68.032, + "args": { + "External id": 1432129,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851286350.666, "dur": 62.678, + "args": { + "External id": 1432130,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286354.901, "dur": 7.302, + "args": { + "External id": 1432131,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851286363.930, "dur": 48.931, + "args": { + "External id": 1432132,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2115 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.21", "pid": 2338706, "tid": 2379422, + "ts": 6413851286576.608, "dur": 673.302, + "args": { + "External id": 1432133,"Record function id": 0, "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413851286594.488, "dur": 642.283, + "args": { + "External id": 1432134,"Record function id": 0, "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851286653.862, "dur": 5.032, + "args": { + "External id": 1432135,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851286675.203, "dur": 36.807, + "args": { + "External id": 1432136,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286679.914, "dur": 1.904, + "args": { + "External id": 1432137,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286686.483, "dur": 0.456, + "args": { + "External id": 1432138,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286688.370, "dur": 0.335, + "args": { + "External id": 1432139,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286690.253, "dur": 0.477, + "args": { + "External id": 1432140,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286694.497, "dur": 0.433, + "args": { + "External id": 1432141,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286696.792, "dur": 2.231, + "args": { + "External id": 1432142,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286700.290, "dur": 1.762, + "args": { + "External id": 1432143,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286703.487, "dur": 0.358, + "args": { + "External id": 1432144,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286705.276, "dur": 0.538, + "args": { + "External id": 1432145,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851286723.466, "dur": 41.763, + "args": { + "External id": 1432146,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851286797.244, "dur": 123.114, + "args": { + "External id": 1432147,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851286806.844, "dur": 3.789, + "args": { + "External id": 1432148,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851286815.812, "dur": 10.488, + "args": { + "External id": 1432149,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851286820.093, "dur": 5.789, + "args": { + "External id": 1432150,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286823.661, "dur": 0.618, + "args": { + "External id": 1432151,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851286833.594, "dur": 37.024, + "args": { + "External id": 1432152,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286836.403, "dur": 2.313, + "args": { + "External id": 1432153,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286840.848, "dur": 0.493, + "args": { + "External id": 1432154,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286842.699, "dur": 3.075, + "args": { + "External id": 1432155,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286849.771, "dur": 0.248, + "args": { + "External id": 1432156,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286851.762, "dur": 0.423, + "args": { + "External id": 1432157,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286853.721, "dur": 0.285, + "args": { + "External id": 1432158,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286857.374, "dur": 0.403, + "args": { + "External id": 1432159,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286859.553, "dur": 0.392, + "args": { + "External id": 1432160,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851286861.275, "dur": 1.894, + "args": { + "External id": 1432161,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851286882.713, "dur": 29.695, + "args": { + "External id": 1432162,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851286964.247, "dur": 189.244, + "args": { + "External id": 1432163,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851287016.108, "dur": 133.095, + "args": { + "External id": 1432164,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2147, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851287029.497, "dur": 114.778, + "args": { + "External id": 1432165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851287175.354, "dur": 2.015, + "args": { + "External id": 1432166,"Record function id": 0, "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": 2149, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851287265.852, "dur": 1841.009, + "args": { + "External id": 1432167,"Sequence number": 15348704, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2150 + } + }, + { + "ph": "f", "id": 178, "pid": 2338706, "tid": 2379422, "ts": 6413851287265.852, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851287385.243, "dur": 103.939, + "args": { + "External id": 1432168,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851287534.991, "dur": 43.593, + "args": { + "External id": 1432169,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851287595.318, "dur": 48.040, + "args": { + "External id": 1432170,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851287665.629, "dur": 32.551, + "args": { + "External id": 1432171,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851287704.764, "dur": 31.874, + "args": { + "External id": 1432172,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851287742.976, "dur": 27.587, + "args": { + "External id": 1432173,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851287779.404, "dur": 28.444, + "args": { + "External id": 1432174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851287838.678, "dur": 24.633, + "args": { + "External id": 1432175,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851287884.053, "dur": 28.801, + "args": { + "External id": 1432176,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851287935.972, "dur": 22.482, + "args": { + "External id": 1432177,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851287972.875, "dur": 35.736, + "args": { + "External id": 1432178,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288019.955, "dur": 76.942, + "args": { + "External id": 1432179,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288103.577, "dur": 36.054, + "args": { + "External id": 1432180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851288174.272, "dur": 267.778, + "args": { + "External id": 1432181,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851288263.512, "dur": 6.445, + "args": { + "External id": 1432182,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851288271.906, "dur": 4.161, + "args": { + "External id": 1432183,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851288277.469, "dur": 3.862, + "args": { + "External id": 1432184,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851288282.467, "dur": 1.891, + "args": { + "External id": 1432185,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851288331.425, "dur": 7.806, + "args": { + "External id": 1432186,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851288336.077, "dur": 2.911, + "args": { + "External id": 1432187,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851288341.526, "dur": 34.547, + "args": { + "External id": 1432188,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851288346.766, "dur": 3.274, + "args": { + "External id": 1432189,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851288377.435, "dur": 1.731, + "args": { + "External id": 1432190,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851288378.546, "dur": 0.531, + "args": { + "External id": 1432191,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851288380.225, "dur": 15.954, + "args": { + "External id": 1432192,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851288382.159, "dur": 0.622, + "args": { + "External id": 1432193,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851288486.033, "dur": 31.149, + "args": { + "External id": 1432194,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851288537.694, "dur": 32.111, + "args": { + "External id": 1432195,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288585.394, "dur": 48.905, + "args": { + "External id": 1432196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288640.918, "dur": 38.486, + "args": { + "External id": 1432197,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288689.901, "dur": 23.510, + "args": { + "External id": 1432198,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288718.913, "dur": 29.498, + "args": { + "External id": 1432199,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288758.648, "dur": 28.307, + "args": { + "External id": 1432200,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851288795.109, "dur": 29.390, + "args": { + "External id": 1432201,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851288847.248, "dur": 24.223, + "args": { + "External id": 1432202,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851288891.088, "dur": 24.098, + "args": { + "External id": 1432203,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851288932.350, "dur": 16.842, + "args": { + "External id": 1432204,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851288969.901, "dur": 33.340, + "args": { + "External id": 1432205,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851289021.918, "dur": 16.448, + "args": { + "External id": 1432206,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289160.439, "dur": 16.230, + "args": { + "External id": 1432207,"Record function id": 0, "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289164.000, "dur": 11.736, + "args": { + "External id": 1432208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289168.591, "dur": 5.954, + "args": { + "External id": 1432209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289170.126, "dur": 4.335, + "args": { + "External id": 1432210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289180.456, "dur": 5.042, + "args": { + "External id": 1432211,"Record function id": 0, "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289181.930, "dur": 2.965, + "args": { + "External id": 1432212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289182.859, "dur": 1.487, + "args": { + "External id": 1432213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289183.476, "dur": 0.756, + "args": { + "External id": 1432214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289188.786, "dur": 7.211, + "args": { + "External id": 1432215,"Record function id": 0, "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289190.224, "dur": 5.314, + "args": { + "External id": 1432216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289190.788, "dur": 4.346, + "args": { + "External id": 1432217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289191.613, "dur": 3.438, + "args": { + "External id": 1432218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289199.319, "dur": 5.006, + "args": { + "External id": 1432219,"Record function id": 0, "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289200.739, "dur": 3.142, + "args": { + "External id": 1432220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289201.755, "dur": 1.517, + "args": { + "External id": 1432221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289202.402, "dur": 0.761, + "args": { + "External id": 1432222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289207.506, "dur": 4.022, + "args": { + "External id": 1432223,"Record function id": 0, "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289208.866, "dur": 2.271, + "args": { + "External id": 1432224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289209.472, "dur": 1.076, + "args": { + "External id": 1432225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289209.768, "dur": 0.715, + "args": { + "External id": 1432226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289214.568, "dur": 4.298, + "args": { + "External id": 1432227,"Record function id": 0, "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289215.941, "dur": 2.518, + "args": { + "External id": 1432228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289216.556, "dur": 1.327, + "args": { + "External id": 1432229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289217.075, "dur": 0.733, + "args": { + "External id": 1432230,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289224.801, "dur": 4.030, + "args": { + "External id": 1432231,"Record function id": 0, "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289225.811, "dur": 2.616, + "args": { + "External id": 1432232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289226.324, "dur": 1.469, + "args": { + "External id": 1432233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289226.881, "dur": 0.847, + "args": { + "External id": 1432234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289231.881, "dur": 7.372, + "args": { + "External id": 1432235,"Record function id": 0, "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289233.220, "dur": 5.525, + "args": { + "External id": 1432236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289233.984, "dur": 4.204, + "args": { + "External id": 1432237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289237.441, "dur": 0.681, + "args": { + "External id": 1432238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289243.948, "dur": 4.574, + "args": { + "External id": 1432239,"Record function id": 0, "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851289245.193, "dur": 2.918, + "args": { + "External id": 1432240,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289246.127, "dur": 1.372, + "args": { + "External id": 1432241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851289246.749, "dur": 0.685, + "args": { + "External id": 1432242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851289252.903, "dur": 73040.762, + "args": { + "External id": 1432243,"Record function id": 0, "Sequence number": 15348703, "Fwd thread id": 1, "Ev Idx": 2226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851289254.447, "dur": 73029.561, + "args": { + "External id": 1432244,"Sequence number": 15348703, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2227 + } + }, + { + "ph": "f", "id": 179, "pid": 2338706, "tid": 2379422, "ts": 6413851289254.447, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413851289287.483, "dur": 42.881, + "args": { + "External id": 1432245,"Record function id": 0, "Ev Idx": 2228 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413851289338.165, "dur": 67.700, + "args": { + "External id": 1432246,"Record function id": 0, "Ev Idx": 2229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413851289411.665, "dur": 72863.704, + "args": { + "External id": 1432247,"Record function id": 0, "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851289503.600, "dur": 7.394, + "args": { + "External id": 1432248,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851289520.486, "dur": 6.915, + "args": { + "External id": 1432249,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851289559.576, "dur": 71786.900, + "args": { + "External id": 1432250,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851289577.284, "dur": 71755.094, + "args": { + "External id": 1432251,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851289734.317, "dur": 18.272, + "args": { + "External id": 1432252,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851289773.346, "dur": 71514.362, + "args": { + "External id": 1432253,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851289776.270, "dur": 71509.752, + "args": { + "External id": 1432254,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851289780.413, "dur": 12.511, + "args": { + "External id": 1432255,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851289795.671, "dur": 71484.876, + "args": { + "External id": 1432256,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851361457.896, "dur": 13.033, + "args": { + "External id": 1432257,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851361461.592, "dur": 8.903, + "args": { + "External id": 1432258,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851361502.529, "dur": 388.257, + "args": { + "External id": 1432259,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851361535.436, "dur": 350.386, + "args": { + "External id": 1432260,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2243, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851361551.383, "dur": 326.261, + "args": { + "External id": 1432261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851361915.379, "dur": 2.190, + "args": { + "External id": 1432262,"Record function id": 0, "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": 2245, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851361993.940, "dur": 7.491, + "args": { + "External id": 1432263,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362087.259, "dur": 2.397, + "args": { + "External id": 1432264,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362112.290, "dur": 4.047, + "args": { + "External id": 1432265,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362130.771, "dur": 1.095, + "args": { + "External id": 1432266,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362146.364, "dur": 0.916, + "args": { + "External id": 1432267,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362159.580, "dur": 0.991, + "args": { + "External id": 1432268,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362172.586, "dur": 3.236, + "args": { + "External id": 1432269,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362188.638, "dur": 3.564, + "args": { + "External id": 1432270,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362206.722, "dur": 1.114, + "args": { + "External id": 1432271,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851362311.040, "dur": 3048.414, + "args": { + "External id": 1432272,"Record function id": 0, "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413851362331.957, "dur": 1159.551, + "args": { + "External id": 1432273,"Record function id": 0, "Ev Idx": 2256 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413851362347.443, "dur": 351.033, + "args": { + "External id": 1432274,"Record function id": 0, "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362444.498, "dur": 4.265, + "args": { + "External id": 1432275,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362452.019, "dur": 1.137, + "args": { + "External id": 1432276,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362455.023, "dur": 2.835, + "args": { + "External id": 1432277,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362459.742, "dur": 1.163, + "args": { + "External id": 1432278,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362462.396, "dur": 1.066, + "args": { + "External id": 1432279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362464.712, "dur": 0.926, + "args": { + "External id": 1432280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362467.511, "dur": 2.875, + "args": { + "External id": 1432281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362475.598, "dur": 0.855, + "args": { + "External id": 1432282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362478.040, "dur": 0.807, + "args": { + "External id": 1432283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851362480.376, "dur": 0.779, + "args": { + "External id": 1432284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851362499.353, "dur": 168.498, + "args": { + "External id": 1432285,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851362517.054, "dur": 145.354, + "args": { + "External id": 1432286,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851362543.678, "dur": 18.627, + "args": { + "External id": 1432287,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851362566.289, "dur": 66.820, + "args": { + "External id": 1432288,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851362568.785, "dur": 63.926, + "args": { + "External id": 1432289,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362575.278, "dur": 6.068, + "args": { + "External id": 1432290,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851362582.942, "dur": 49.044, + "args": { + "External id": 1432291,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2274 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.20", "pid": 2338706, "tid": 2379422, + "ts": 6413851362795.306, "dur": 688.272, + "args": { + "External id": 1432292,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413851362812.233, "dur": 658.321, + "args": { + "External id": 1432293,"Record function id": 0, "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851362872.385, "dur": 5.053, + "args": { + "External id": 1432294,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851362894.179, "dur": 39.839, + "args": { + "External id": 1432295,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362899.969, "dur": 1.578, + "args": { + "External id": 1432296,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362903.789, "dur": 2.569, + "args": { + "External id": 1432297,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362907.967, "dur": 0.342, + "args": { + "External id": 1432298,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362910.157, "dur": 0.327, + "args": { + "External id": 1432299,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362913.864, "dur": 0.488, + "args": { + "External id": 1432300,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362916.105, "dur": 2.637, + "args": { + "External id": 1432301,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362920.598, "dur": 0.418, + "args": { + "External id": 1432302,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362924.753, "dur": 0.251, + "args": { + "External id": 1432303,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851362926.496, "dur": 0.240, + "args": { + "External id": 1432304,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851362944.993, "dur": 61.451, + "args": { + "External id": 1432305,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851363041.991, "dur": 166.636, + "args": { + "External id": 1432306,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851363087.167, "dur": 5.827, + "args": { + "External id": 1432307,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851363100.268, "dur": 11.323, + "args": { + "External id": 1432308,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851363104.607, "dur": 6.535, + "args": { + "External id": 1432309,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363108.542, "dur": 0.929, + "args": { + "External id": 1432310,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851363119.665, "dur": 34.439, + "args": { + "External id": 1432311,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363122.814, "dur": 0.481, + "args": { + "External id": 1432312,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363127.449, "dur": 0.345, + "args": { + "External id": 1432313,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363129.199, "dur": 2.439, + "args": { + "External id": 1432314,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363133.321, "dur": 2.185, + "args": { + "External id": 1432315,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363136.974, "dur": 0.314, + "args": { + "External id": 1432316,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363138.756, "dur": 0.495, + "args": { + "External id": 1432317,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363142.684, "dur": 0.331, + "args": { + "External id": 1432318,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363144.481, "dur": 0.371, + "args": { + "External id": 1432319,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851363146.385, "dur": 0.286, + "args": { + "External id": 1432320,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851363166.324, "dur": 33.359, + "args": { + "External id": 1432321,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851363258.305, "dur": 137.567, + "args": { + "External id": 1432322,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851363290.125, "dur": 102.265, + "args": { + "External id": 1432323,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2306, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851363305.603, "dur": 82.300, + "args": { + "External id": 1432324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851363414.278, "dur": 2.103, + "args": { + "External id": 1432325,"Record function id": 0, "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": 2308, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851363499.520, "dur": 1834.054, + "args": { + "External id": 1432326,"Sequence number": 15348702, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2309 + } + }, + { + "ph": "f", "id": 180, "pid": 2338706, "tid": 2379422, "ts": 6413851363499.520, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851363616.641, "dur": 103.569, + "args": { + "External id": 1432327,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851363765.426, "dur": 41.134, + "args": { + "External id": 1432328,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851363824.677, "dur": 46.747, + "args": { + "External id": 1432329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851363883.111, "dur": 30.138, + "args": { + "External id": 1432330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851363919.509, "dur": 31.486, + "args": { + "External id": 1432331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851363957.415, "dur": 48.530, + "args": { + "External id": 1432332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364016.922, "dur": 32.116, + "args": { + "External id": 1432333,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851364119.659, "dur": 28.425, + "args": { + "External id": 1432334,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851364169.099, "dur": 29.032, + "args": { + "External id": 1432335,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851364224.387, "dur": 19.841, + "args": { + "External id": 1432336,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851364258.787, "dur": 17.828, + "args": { + "External id": 1432337,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364284.147, "dur": 42.998, + "args": { + "External id": 1432338,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364331.463, "dur": 31.864, + "args": { + "External id": 1432339,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851364398.431, "dur": 251.238, + "args": { + "External id": 1432340,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851364479.596, "dur": 6.173, + "args": { + "External id": 1432341,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851364487.918, "dur": 2.222, + "args": { + "External id": 1432342,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851364491.240, "dur": 2.698, + "args": { + "External id": 1432343,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851364494.980, "dur": 2.067, + "args": { + "External id": 1432344,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851364539.943, "dur": 7.595, + "args": { + "External id": 1432345,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851364544.670, "dur": 2.681, + "args": { + "External id": 1432346,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851364549.824, "dur": 36.045, + "args": { + "External id": 1432347,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851364555.419, "dur": 5.481, + "args": { + "External id": 1432348,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851364587.544, "dur": 1.665, + "args": { + "External id": 1432349,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851364588.461, "dur": 0.661, + "args": { + "External id": 1432350,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851364590.656, "dur": 14.362, + "args": { + "External id": 1432351,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851364592.868, "dur": 0.703, + "args": { + "External id": 1432352,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851364688.031, "dur": 28.105, + "args": { + "External id": 1432353,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851364735.324, "dur": 16.654, + "args": { + "External id": 1432354,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364759.105, "dur": 39.111, + "args": { + "External id": 1432355,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364804.267, "dur": 35.698, + "args": { + "External id": 1432356,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364849.663, "dur": 20.360, + "args": { + "External id": 1432357,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364875.458, "dur": 30.364, + "args": { + "External id": 1432358,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364916.466, "dur": 26.550, + "args": { + "External id": 1432359,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851364969.873, "dur": 65.615, + "args": { + "External id": 1432360,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851365096.402, "dur": 32.678, + "args": { + "External id": 1432361,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851365162.888, "dur": 32.018, + "args": { + "External id": 1432362,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851365216.121, "dur": 17.908, + "args": { + "External id": 1432363,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851365253.276, "dur": 15.547, + "args": { + "External id": 1432364,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851365286.526, "dur": 16.795, + "args": { + "External id": 1432365,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365382.217, "dur": 19.535, + "args": { + "External id": 1432366,"Record function id": 0, "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365386.194, "dur": 14.666, + "args": { + "External id": 1432367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365390.857, "dur": 8.924, + "args": { + "External id": 1432368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365393.071, "dur": 6.594, + "args": { + "External id": 1432369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365405.741, "dur": 5.632, + "args": { + "External id": 1432370,"Record function id": 0, "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365407.381, "dur": 3.523, + "args": { + "External id": 1432371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365408.447, "dur": 1.861, + "args": { + "External id": 1432372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365409.184, "dur": 1.040, + "args": { + "External id": 1432373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365414.634, "dur": 7.030, + "args": { + "External id": 1432374,"Record function id": 0, "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365416.011, "dur": 5.227, + "args": { + "External id": 1432375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365416.758, "dur": 3.919, + "args": { + "External id": 1432376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365417.474, "dur": 3.117, + "args": { + "External id": 1432377,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365425.001, "dur": 4.433, + "args": { + "External id": 1432378,"Record function id": 0, "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365426.351, "dur": 2.641, + "args": { + "External id": 1432379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365427.169, "dur": 1.406, + "args": { + "External id": 1432380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365427.584, "dur": 0.909, + "args": { + "External id": 1432381,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365432.525, "dur": 4.664, + "args": { + "External id": 1432382,"Record function id": 0, "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365434.059, "dur": 2.678, + "args": { + "External id": 1432383,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365434.721, "dur": 1.417, + "args": { + "External id": 1432384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365435.333, "dur": 0.729, + "args": { + "External id": 1432385,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365440.469, "dur": 4.593, + "args": { + "External id": 1432386,"Record function id": 0, "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365441.924, "dur": 2.713, + "args": { + "External id": 1432387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365442.681, "dur": 1.556, + "args": { + "External id": 1432388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365443.452, "dur": 0.716, + "args": { + "External id": 1432389,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365448.365, "dur": 4.560, + "args": { + "External id": 1432390,"Record function id": 0, "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365449.639, "dur": 2.875, + "args": { + "External id": 1432391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365450.434, "dur": 1.651, + "args": { + "External id": 1432392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365451.144, "dur": 0.877, + "args": { + "External id": 1432393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365456.016, "dur": 7.200, + "args": { + "External id": 1432394,"Record function id": 0, "Ev Idx": 2377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365458.071, "dur": 4.730, + "args": { + "External id": 1432395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365458.705, "dur": 3.365, + "args": { + "External id": 1432396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365461.226, "dur": 0.749, + "args": { + "External id": 1432397,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365467.752, "dur": 4.616, + "args": { + "External id": 1432398,"Record function id": 0, "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851365469.192, "dur": 2.762, + "args": { + "External id": 1432399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365469.634, "dur": 1.751, + "args": { + "External id": 1432400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851365470.500, "dur": 0.801, + "args": { + "External id": 1432401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851365476.500, "dur": 71691.589, + "args": { + "External id": 1432402,"Record function id": 0, "Sequence number": 15348701, "Fwd thread id": 1, "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851365477.716, "dur": 71678.933, + "args": { + "External id": 1432403,"Sequence number": 15348701, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2386 + } + }, + { + "ph": "f", "id": 181, "pid": 2338706, "tid": 2379422, "ts": 6413851365477.716, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413851365509.504, "dur": 39.446, + "args": { + "External id": 1432404,"Record function id": 0, "Ev Idx": 2387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413851365556.956, "dur": 68.321, + "args": { + "External id": 1432405,"Record function id": 0, "Ev Idx": 2388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413851365630.650, "dur": 71516.437, + "args": { + "External id": 1432406,"Record function id": 0, "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851365719.870, "dur": 7.000, + "args": { + "External id": 1432407,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851365736.690, "dur": 6.727, + "args": { + "External id": 1432408,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851365757.507, "dur": 70442.188, + "args": { + "External id": 1432409,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851365788.501, "dur": 70397.200, + "args": { + "External id": 1432410,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851365890.125, "dur": 18.379, + "args": { + "External id": 1432411,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851365931.296, "dur": 70207.065, + "args": { + "External id": 1432412,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851365934.626, "dur": 70202.319, + "args": { + "External id": 1432413,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851365939.369, "dur": 11.053, + "args": { + "External id": 1432414,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851365952.628, "dur": 70178.859, + "args": { + "External id": 1432415,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851436313.346, "dur": 13.302, + "args": { + "External id": 1432416,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851436317.162, "dur": 9.065, + "args": { + "External id": 1432417,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851436357.693, "dur": 383.391, + "args": { + "External id": 1432418,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851436392.148, "dur": 343.865, + "args": { + "External id": 1432419,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2402, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851436407.217, "dur": 323.781, + "args": { + "External id": 1432420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851436788.851, "dur": 2.793, + "args": { + "External id": 1432421,"Record function id": 0, "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": 2404, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851436852.742, "dur": 6.820, + "args": { + "External id": 1432422,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851436906.254, "dur": 1.467, + "args": { + "External id": 1432423,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851436926.497, "dur": 3.610, + "args": { + "External id": 1432424,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851436943.655, "dur": 1.160, + "args": { + "External id": 1432425,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851436959.491, "dur": 1.245, + "args": { + "External id": 1432426,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851436973.575, "dur": 0.860, + "args": { + "External id": 1432427,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437012.109, "dur": 4.005, + "args": { + "External id": 1432428,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437029.682, "dur": 3.335, + "args": { + "External id": 1432429,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437046.405, "dur": 1.012, + "args": { + "External id": 1432430,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851437186.227, "dur": 3094.579, + "args": { + "External id": 1432431,"Record function id": 0, "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413851437206.437, "dur": 1157.769, + "args": { + "External id": 1432432,"Record function id": 0, "Ev Idx": 2415 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413851437225.938, "dur": 345.519, + "args": { + "External id": 1432433,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437322.996, "dur": 4.822, + "args": { + "External id": 1432434,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437331.011, "dur": 1.397, + "args": { + "External id": 1432435,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437334.209, "dur": 3.247, + "args": { + "External id": 1432436,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437339.349, "dur": 0.967, + "args": { + "External id": 1432437,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437341.885, "dur": 0.988, + "args": { + "External id": 1432438,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437344.437, "dur": 1.172, + "args": { + "External id": 1432439,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437347.192, "dur": 3.348, + "args": { + "External id": 1432440,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437354.307, "dur": 1.104, + "args": { + "External id": 1432441,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437357.047, "dur": 0.998, + "args": { + "External id": 1432442,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851437359.648, "dur": 0.896, + "args": { + "External id": 1432443,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851437378.407, "dur": 164.477, + "args": { + "External id": 1432444,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851437395.885, "dur": 142.230, + "args": { + "External id": 1432445,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851437422.608, "dur": 18.043, + "args": { + "External id": 1432446,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851437444.388, "dur": 64.195, + "args": { + "External id": 1432447,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851437447.042, "dur": 61.199, + "args": { + "External id": 1432448,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437451.656, "dur": 5.931, + "args": { + "External id": 1432449,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851437459.338, "dur": 48.358, + "args": { + "External id": 1432450,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2433 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 2338706, "tid": 2379422, + "ts": 6413851437670.434, "dur": 683.833, + "args": { + "External id": 1432451,"Record function id": 0, "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413851437692.518, "dur": 649.394, + "args": { + "External id": 1432452,"Record function id": 0, "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851437757.381, "dur": 4.485, + "args": { + "External id": 1432453,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851437777.636, "dur": 40.069, + "args": { + "External id": 1432454,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437782.641, "dur": 3.477, + "args": { + "External id": 1432455,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437788.149, "dur": 0.487, + "args": { + "External id": 1432456,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437790.361, "dur": 0.547, + "args": { + "External id": 1432457,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437794.177, "dur": 0.485, + "args": { + "External id": 1432458,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437795.951, "dur": 0.593, + "args": { + "External id": 1432459,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437798.068, "dur": 2.790, + "args": { + "External id": 1432460,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437804.925, "dur": 0.334, + "args": { + "External id": 1432461,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437806.729, "dur": 0.308, + "args": { + "External id": 1432462,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437808.658, "dur": 2.426, + "args": { + "External id": 1432463,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851437829.032, "dur": 43.778, + "args": { + "External id": 1432464,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851437904.098, "dur": 146.805, + "args": { + "External id": 1432465,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851437913.547, "dur": 3.904, + "args": { + "External id": 1432466,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851437922.832, "dur": 11.217, + "args": { + "External id": 1432467,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851437927.032, "dur": 6.575, + "args": { + "External id": 1432468,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437931.498, "dur": 0.676, + "args": { + "External id": 1432469,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851437940.924, "dur": 52.824, + "args": { + "External id": 1432470,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437943.208, "dur": 0.558, + "args": { + "External id": 1432471,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437945.507, "dur": 0.479, + "args": { + "External id": 1432472,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437947.210, "dur": 5.387, + "args": { + "External id": 1432473,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437953.966, "dur": 0.430, + "args": { + "External id": 1432474,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437955.827, "dur": 0.501, + "args": { + "External id": 1432475,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437959.637, "dur": 0.332, + "args": { + "External id": 1432476,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437961.782, "dur": 0.378, + "args": { + "External id": 1432477,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437963.512, "dur": 0.699, + "args": { + "External id": 1432478,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851437967.692, "dur": 0.402, + "args": { + "External id": 1432479,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851438009.762, "dur": 33.048, + "args": { + "External id": 1432480,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851438137.052, "dur": 129.844, + "args": { + "External id": 1432481,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851438169.284, "dur": 93.970, + "args": { + "External id": 1432482,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2465, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851438181.288, "dur": 77.851, + "args": { + "External id": 1432483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851438285.064, "dur": 1.797, + "args": { + "External id": 1432484,"Record function id": 0, "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": 2467, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851438372.253, "dur": 1879.424, + "args": { + "External id": 1432485,"Sequence number": 15348700, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2468 + } + }, + { + "ph": "f", "id": 182, "pid": 2338706, "tid": 2379422, "ts": 6413851438372.253, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851438489.814, "dur": 105.715, + "args": { + "External id": 1432486,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851438639.917, "dur": 43.092, + "args": { + "External id": 1432487,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851438701.014, "dur": 47.657, + "args": { + "External id": 1432488,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851438761.465, "dur": 30.799, + "args": { + "External id": 1432489,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851438798.375, "dur": 31.593, + "args": { + "External id": 1432490,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851438836.395, "dur": 26.418, + "args": { + "External id": 1432491,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851438870.752, "dur": 29.028, + "args": { + "External id": 1432492,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851438927.513, "dur": 22.310, + "args": { + "External id": 1432493,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851438970.995, "dur": 51.640, + "args": { + "External id": 1432494,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851439087.127, "dur": 22.658, + "args": { + "External id": 1432495,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851439129.287, "dur": 15.267, + "args": { + "External id": 1432496,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439153.724, "dur": 43.789, + "args": { + "External id": 1432497,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439201.617, "dur": 32.953, + "args": { + "External id": 1432498,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851439269.514, "dur": 261.067, + "args": { + "External id": 1432499,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851439352.494, "dur": 6.529, + "args": { + "External id": 1432500,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851439361.355, "dur": 3.401, + "args": { + "External id": 1432501,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851439366.087, "dur": 2.628, + "args": { + "External id": 1432502,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851439369.976, "dur": 2.358, + "args": { + "External id": 1432503,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851439417.990, "dur": 9.573, + "args": { + "External id": 1432504,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851439424.723, "dur": 2.677, + "args": { + "External id": 1432505,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851439429.736, "dur": 35.494, + "args": { + "External id": 1432506,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851439436.040, "dur": 4.000, + "args": { + "External id": 1432507,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851439466.874, "dur": 1.510, + "args": { + "External id": 1432508,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851439467.803, "dur": 0.498, + "args": { + "External id": 1432509,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851439469.590, "dur": 15.341, + "args": { + "External id": 1432510,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851439471.537, "dur": 0.467, + "args": { + "External id": 1432511,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851439571.851, "dur": 27.614, + "args": { + "External id": 1432512,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851439619.174, "dur": 16.530, + "args": { + "External id": 1432513,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439643.039, "dur": 40.733, + "args": { + "External id": 1432514,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439690.016, "dur": 36.299, + "args": { + "External id": 1432515,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439736.727, "dur": 23.039, + "args": { + "External id": 1432516,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439765.714, "dur": 49.337, + "args": { + "External id": 1432517,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439830.747, "dur": 37.791, + "args": { + "External id": 1432518,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851439876.201, "dur": 28.887, + "args": { + "External id": 1432519,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851439929.578, "dur": 25.397, + "args": { + "External id": 1432520,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851440044.989, "dur": 62.250, + "args": { + "External id": 1432521,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851440132.948, "dur": 17.900, + "args": { + "External id": 1432522,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851440169.070, "dur": 16.915, + "args": { + "External id": 1432523,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851440202.208, "dur": 15.817, + "args": { + "External id": 1432524,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440304.118, "dur": 15.743, + "args": { + "External id": 1432525,"Record function id": 0, "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440307.844, "dur": 11.031, + "args": { + "External id": 1432526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440312.375, "dur": 5.599, + "args": { + "External id": 1432527,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440313.872, "dur": 4.009, + "args": { + "External id": 1432528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440323.722, "dur": 4.937, + "args": { + "External id": 1432529,"Record function id": 0, "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440325.317, "dur": 2.920, + "args": { + "External id": 1432530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440326.050, "dur": 1.751, + "args": { + "External id": 1432531,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440326.766, "dur": 0.928, + "args": { + "External id": 1432532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440332.011, "dur": 6.363, + "args": { + "External id": 1432533,"Record function id": 0, "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440333.208, "dur": 4.693, + "args": { + "External id": 1432534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440333.785, "dur": 3.707, + "args": { + "External id": 1432535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440334.429, "dur": 2.968, + "args": { + "External id": 1432536,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440341.613, "dur": 4.079, + "args": { + "External id": 1432537,"Record function id": 0, "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440343.112, "dur": 2.165, + "args": { + "External id": 1432538,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440343.697, "dur": 1.175, + "args": { + "External id": 1432539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440344.041, "dur": 0.725, + "args": { + "External id": 1432540,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440349.334, "dur": 4.280, + "args": { + "External id": 1432541,"Record function id": 0, "Ev Idx": 2524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440350.588, "dur": 2.607, + "args": { + "External id": 1432542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440351.380, "dur": 1.216, + "args": { + "External id": 1432543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440351.797, "dur": 0.735, + "args": { + "External id": 1432544,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440357.049, "dur": 3.796, + "args": { + "External id": 1432545,"Record function id": 0, "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440358.139, "dur": 2.279, + "args": { + "External id": 1432546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440358.806, "dur": 1.061, + "args": { + "External id": 1432547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440359.258, "dur": 0.542, + "args": { + "External id": 1432548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440364.266, "dur": 4.346, + "args": { + "External id": 1432549,"Record function id": 0, "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440365.592, "dur": 2.613, + "args": { + "External id": 1432550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440366.204, "dur": 1.448, + "args": { + "External id": 1432551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440366.921, "dur": 0.658, + "args": { + "External id": 1432552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440372.025, "dur": 6.452, + "args": { + "External id": 1432553,"Record function id": 0, "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440373.199, "dur": 4.880, + "args": { + "External id": 1432554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440374.163, "dur": 3.512, + "args": { + "External id": 1432555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440376.836, "dur": 0.774, + "args": { + "External id": 1432556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440381.952, "dur": 4.305, + "args": { + "External id": 1432557,"Record function id": 0, "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851440383.283, "dur": 2.579, + "args": { + "External id": 1432558,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440383.888, "dur": 1.504, + "args": { + "External id": 1432559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851440384.432, "dur": 0.898, + "args": { + "External id": 1432560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851440390.446, "dur": 61985.283, + "args": { + "External id": 1432561,"Record function id": 0, "Sequence number": 15348699, "Fwd thread id": 1, "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851440391.916, "dur": 61973.516, + "args": { + "External id": 1432562,"Sequence number": 15348699, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2545 + } + }, + { + "ph": "f", "id": 183, "pid": 2338706, "tid": 2379422, "ts": 6413851440391.916, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413851440424.344, "dur": 42.057, + "args": { + "External id": 1432563,"Record function id": 0, "Ev Idx": 2546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413851440473.954, "dur": 71.894, + "args": { + "External id": 1432564,"Record function id": 0, "Ev Idx": 2547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413851440551.438, "dur": 61805.106, + "args": { + "External id": 1432565,"Record function id": 0, "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851440642.030, "dur": 7.311, + "args": { + "External id": 1432566,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851440659.064, "dur": 6.784, + "args": { + "External id": 1432567,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851440680.061, "dur": 60601.065, + "args": { + "External id": 1432568,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851440697.301, "dur": 60570.411, + "args": { + "External id": 1432569,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851440795.749, "dur": 18.322, + "args": { + "External id": 1432570,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851440836.286, "dur": 60386.991, + "args": { + "External id": 1432571,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851440839.028, "dur": 60383.093, + "args": { + "External id": 1432572,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851440846.468, "dur": 9.529, + "args": { + "External id": 1432573,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851440874.922, "dur": 60341.501, + "args": { + "External id": 1432574,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851501393.938, "dur": 13.094, + "args": { + "External id": 1432575,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851501397.895, "dur": 8.669, + "args": { + "External id": 1432576,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851501537.106, "dur": 422.182, + "args": { + "External id": 1432577,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851501573.340, "dur": 380.748, + "args": { + "External id": 1432578,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2561, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851501587.348, "dur": 361.048, + "args": { + "External id": 1432579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851502001.676, "dur": 3.521, + "args": { + "External id": 1432580,"Record function id": 0, "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": 2563, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502115.682, "dur": 7.522, + "args": { + "External id": 1432581,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502172.704, "dur": 1.403, + "args": { + "External id": 1432582,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502192.167, "dur": 5.800, + "args": { + "External id": 1432583,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502212.368, "dur": 0.903, + "args": { + "External id": 1432584,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502228.740, "dur": 0.725, + "args": { + "External id": 1432585,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502242.192, "dur": 0.909, + "args": { + "External id": 1432586,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502255.350, "dur": 2.897, + "args": { + "External id": 1432587,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502272.360, "dur": 3.466, + "args": { + "External id": 1432588,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502288.357, "dur": 2.881, + "args": { + "External id": 1432589,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851502393.496, "dur": 3058.582, + "args": { + "External id": 1432590,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413851502415.940, "dur": 1147.788, + "args": { + "External id": 1432591,"Record function id": 0, "Ev Idx": 2574 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413851502432.531, "dur": 351.646, + "args": { + "External id": 1432592,"Record function id": 0, "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502531.743, "dur": 4.229, + "args": { + "External id": 1432593,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502539.025, "dur": 1.347, + "args": { + "External id": 1432594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502542.485, "dur": 3.244, + "args": { + "External id": 1432595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502547.728, "dur": 1.186, + "args": { + "External id": 1432596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502550.573, "dur": 0.806, + "args": { + "External id": 1432597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502552.768, "dur": 1.086, + "args": { + "External id": 1432598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502555.712, "dur": 3.338, + "args": { + "External id": 1432599,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502562.972, "dur": 1.174, + "args": { + "External id": 1432600,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502565.735, "dur": 1.211, + "args": { + "External id": 1432601,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851502568.620, "dur": 1.122, + "args": { + "External id": 1432602,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851502587.818, "dur": 165.070, + "args": { + "External id": 1432603,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851502604.812, "dur": 143.359, + "args": { + "External id": 1432604,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851502626.119, "dur": 17.620, + "args": { + "External id": 1432605,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851502649.856, "dur": 67.808, + "args": { + "External id": 1432606,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851502653.085, "dur": 64.212, + "args": { + "External id": 1432607,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851502657.428, "dur": 6.098, + "args": { + "External id": 1432608,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851502665.207, "dur": 51.231, + "args": { + "External id": 1432609,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 2338706, "tid": 2379422, + "ts": 6413851502877.825, "dur": 677.923, + "args": { + "External id": 1432610,"Record function id": 0, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413851502896.028, "dur": 645.748, + "args": { + "External id": 1432611,"Record function id": 0, "Ev Idx": 2594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851502959.444, "dur": 5.076, + "args": { + "External id": 1432612,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851503000.865, "dur": 38.720, + "args": { + "External id": 1432613,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503006.531, "dur": 1.837, + "args": { + "External id": 1432614,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503010.850, "dur": 1.875, + "args": { + "External id": 1432615,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503014.489, "dur": 0.630, + "args": { + "External id": 1432616,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503016.554, "dur": 0.567, + "args": { + "External id": 1432617,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503020.081, "dur": 0.497, + "args": { + "External id": 1432618,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503021.968, "dur": 2.680, + "args": { + "External id": 1432619,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503026.119, "dur": 0.460, + "args": { + "External id": 1432620,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503028.932, "dur": 0.256, + "args": { + "External id": 1432621,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503030.876, "dur": 0.463, + "args": { + "External id": 1432622,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851503052.204, "dur": 79.149, + "args": { + "External id": 1432623,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851503169.804, "dur": 123.305, + "args": { + "External id": 1432624,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851503180.792, "dur": 5.330, + "args": { + "External id": 1432625,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851503191.555, "dur": 11.706, + "args": { + "External id": 1432626,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851503196.245, "dur": 6.590, + "args": { + "External id": 1432627,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503200.573, "dur": 0.707, + "args": { + "External id": 1432628,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851503210.198, "dur": 32.652, + "args": { + "External id": 1432629,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503212.461, "dur": 0.588, + "args": { + "External id": 1432630,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503215.943, "dur": 0.614, + "args": { + "External id": 1432631,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503218.086, "dur": 2.439, + "args": { + "External id": 1432632,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503221.995, "dur": 1.860, + "args": { + "External id": 1432633,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503225.225, "dur": 0.493, + "args": { + "External id": 1432634,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503227.705, "dur": 0.560, + "args": { + "External id": 1432635,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503231.307, "dur": 0.525, + "args": { + "External id": 1432636,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503233.505, "dur": 0.278, + "args": { + "External id": 1432637,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851503235.085, "dur": 0.482, + "args": { + "External id": 1432638,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851503254.924, "dur": 29.874, + "args": { + "External id": 1432639,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851503342.719, "dur": 124.081, + "args": { + "External id": 1432640,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851503374.854, "dur": 88.299, + "args": { + "External id": 1432641,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2624, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851503384.891, "dur": 73.963, + "args": { + "External id": 1432642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851503487.472, "dur": 1.945, + "args": { + "External id": 1432643,"Record function id": 0, "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": 2626, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851503571.861, "dur": 1851.550, + "args": { + "External id": 1432644,"Sequence number": 15348698, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2627 + } + }, + { + "ph": "f", "id": 184, "pid": 2338706, "tid": 2379422, "ts": 6413851503571.861, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851503694.142, "dur": 105.106, + "args": { + "External id": 1432645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851503842.360, "dur": 44.113, + "args": { + "External id": 1432646,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851503904.389, "dur": 47.952, + "args": { + "External id": 1432647,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851503964.657, "dur": 55.834, + "args": { + "External id": 1432648,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504030.624, "dur": 71.691, + "args": { + "External id": 1432649,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504113.853, "dur": 32.772, + "args": { + "External id": 1432650,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504155.594, "dur": 29.140, + "args": { + "External id": 1432651,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851504217.641, "dur": 26.697, + "args": { + "External id": 1432652,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851504264.346, "dur": 27.980, + "args": { + "External id": 1432653,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851504318.782, "dur": 20.270, + "args": { + "External id": 1432654,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851504353.673, "dur": 17.695, + "args": { + "External id": 1432655,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504379.364, "dur": 36.551, + "args": { + "External id": 1432656,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504419.321, "dur": 33.561, + "args": { + "External id": 1432657,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851504487.542, "dur": 255.538, + "args": { + "External id": 1432658,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851504568.183, "dur": 6.547, + "args": { + "External id": 1432659,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851504577.219, "dur": 3.179, + "args": { + "External id": 1432660,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851504581.551, "dur": 2.816, + "args": { + "External id": 1432661,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851504585.667, "dur": 2.355, + "args": { + "External id": 1432662,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851504634.463, "dur": 5.342, + "args": { + "External id": 1432663,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851504636.795, "dur": 2.825, + "args": { + "External id": 1432664,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851504642.445, "dur": 35.440, + "args": { + "External id": 1432665,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851504648.349, "dur": 4.071, + "args": { + "External id": 1432666,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851504679.768, "dur": 2.211, + "args": { + "External id": 1432667,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851504681.234, "dur": 0.656, + "args": { + "External id": 1432668,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851504683.525, "dur": 15.306, + "args": { + "External id": 1432669,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851504685.612, "dur": 0.640, + "args": { + "External id": 1432670,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851504782.675, "dur": 27.441, + "args": { + "External id": 1432671,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851504830.291, "dur": 15.614, + "args": { + "External id": 1432672,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504854.123, "dur": 56.478, + "args": { + "External id": 1432673,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851504923.507, "dur": 44.543, + "args": { + "External id": 1432674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851505000.367, "dur": 29.300, + "args": { + "External id": 1432675,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851505036.806, "dur": 69.366, + "args": { + "External id": 1432676,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851505118.170, "dur": 33.757, + "args": { + "External id": 1432677,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851505160.566, "dur": 34.049, + "args": { + "External id": 1432678,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851505219.297, "dur": 30.805, + "args": { + "External id": 1432679,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851505267.983, "dur": 25.702, + "args": { + "External id": 1432680,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851505310.337, "dur": 16.666, + "args": { + "External id": 1432681,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851505346.304, "dur": 14.347, + "args": { + "External id": 1432682,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851505375.776, "dur": 15.667, + "args": { + "External id": 1432683,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505475.138, "dur": 16.830, + "args": { + "External id": 1432684,"Record function id": 0, "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505478.837, "dur": 12.255, + "args": { + "External id": 1432685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505483.386, "dur": 6.827, + "args": { + "External id": 1432686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505485.685, "dur": 4.397, + "args": { + "External id": 1432687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505495.904, "dur": 5.541, + "args": { + "External id": 1432688,"Record function id": 0, "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505497.168, "dur": 3.774, + "args": { + "External id": 1432689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505498.231, "dur": 2.137, + "args": { + "External id": 1432690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505499.129, "dur": 1.159, + "args": { + "External id": 1432691,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505504.651, "dur": 6.973, + "args": { + "External id": 1432692,"Record function id": 0, "Ev Idx": 2675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505506.328, "dur": 4.881, + "args": { + "External id": 1432693,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505507.001, "dur": 3.707, + "args": { + "External id": 1432694,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505507.439, "dur": 3.198, + "args": { + "External id": 1432695,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505515.114, "dur": 4.127, + "args": { + "External id": 1432696,"Record function id": 0, "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505516.213, "dur": 2.569, + "args": { + "External id": 1432697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505516.763, "dur": 1.526, + "args": { + "External id": 1432698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505517.211, "dur": 1.014, + "args": { + "External id": 1432699,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505522.625, "dur": 4.183, + "args": { + "External id": 1432700,"Record function id": 0, "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505524.272, "dur": 2.138, + "args": { + "External id": 1432701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505524.702, "dur": 1.323, + "args": { + "External id": 1432702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505525.377, "dur": 0.574, + "args": { + "External id": 1432703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505530.099, "dur": 4.242, + "args": { + "External id": 1432704,"Record function id": 0, "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505531.335, "dur": 2.550, + "args": { + "External id": 1432705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505532.031, "dur": 1.438, + "args": { + "External id": 1432706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505532.622, "dur": 0.747, + "args": { + "External id": 1432707,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505537.657, "dur": 3.594, + "args": { + "External id": 1432708,"Record function id": 0, "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505538.958, "dur": 1.861, + "args": { + "External id": 1432709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505539.396, "dur": 0.936, + "args": { + "External id": 1432710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505539.667, "dur": 0.568, + "args": { + "External id": 1432711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505544.633, "dur": 3.900, + "args": { + "External id": 1432712,"Record function id": 0, "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505545.806, "dur": 2.304, + "args": { + "External id": 1432713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505546.437, "dur": 1.176, + "args": { + "External id": 1432714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505546.714, "dur": 0.803, + "args": { + "External id": 1432715,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505551.710, "dur": 4.159, + "args": { + "External id": 1432716,"Record function id": 0, "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851505553.206, "dur": 2.260, + "args": { + "External id": 1432717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505553.653, "dur": 1.305, + "args": { + "External id": 1432718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851505554.149, "dur": 0.690, + "args": { + "External id": 1432719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851505560.299, "dur": 64030.828, + "args": { + "External id": 1432720,"Record function id": 0, "Sequence number": 15348697, "Fwd thread id": 1, "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851505561.758, "dur": 64019.467, + "args": { + "External id": 1432721,"Sequence number": 15348697, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2704 + } + }, + { + "ph": "f", "id": 185, "pid": 2338706, "tid": 2379422, "ts": 6413851505561.758, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413851505590.493, "dur": 38.647, + "args": { + "External id": 1432722,"Record function id": 0, "Ev Idx": 2705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413851505637.175, "dur": 68.999, + "args": { + "External id": 1432723,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413851505711.573, "dur": 63860.831, + "args": { + "External id": 1432724,"Record function id": 0, "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851505804.353, "dur": 6.888, + "args": { + "External id": 1432725,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851505821.240, "dur": 6.300, + "args": { + "External id": 1432726,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851505842.704, "dur": 62805.166, + "args": { + "External id": 1432727,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851505857.985, "dur": 62776.552, + "args": { + "External id": 1432728,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851505970.683, "dur": 40.993, + "args": { + "External id": 1432729,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851506034.765, "dur": 62553.583, + "args": { + "External id": 1432730,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851506037.977, "dur": 62549.347, + "args": { + "External id": 1432731,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851506043.331, "dur": 49.080, + "args": { + "External id": 1432732,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851506096.225, "dur": 62486.043, + "args": { + "External id": 1432733,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851568759.409, "dur": 13.754, + "args": { + "External id": 1432734,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851568764.211, "dur": 8.606, + "args": { + "External id": 1432735,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851568806.200, "dur": 422.358, + "args": { + "External id": 1432736,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851568835.033, "dur": 387.920, + "args": { + "External id": 1432737,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2720, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851568846.977, "dur": 369.644, + "args": { + "External id": 1432738,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851569251.552, "dur": 2.291, + "args": { + "External id": 1432739,"Record function id": 0, "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": 2722, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569319.516, "dur": 6.604, + "args": { + "External id": 1432740,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569375.412, "dur": 1.644, + "args": { + "External id": 1432741,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569395.625, "dur": 3.285, + "args": { + "External id": 1432742,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569413.403, "dur": 0.958, + "args": { + "External id": 1432743,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569427.845, "dur": 1.138, + "args": { + "External id": 1432744,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569441.489, "dur": 0.999, + "args": { + "External id": 1432745,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569455.448, "dur": 3.313, + "args": { + "External id": 1432746,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569471.868, "dur": 3.543, + "args": { + "External id": 1432747,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569504.717, "dur": 1.470, + "args": { + "External id": 1432748,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851569605.895, "dur": 3021.015, + "args": { + "External id": 1432749,"Record function id": 0, "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413851569626.207, "dur": 1124.196, + "args": { + "External id": 1432750,"Record function id": 0, "Ev Idx": 2733 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413851569642.010, "dur": 352.827, + "args": { + "External id": 1432751,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569737.324, "dur": 4.100, + "args": { + "External id": 1432752,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569744.638, "dur": 1.318, + "args": { + "External id": 1432753,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569747.975, "dur": 3.282, + "args": { + "External id": 1432754,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569753.138, "dur": 0.911, + "args": { + "External id": 1432755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569755.951, "dur": 1.200, + "args": { + "External id": 1432756,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569759.078, "dur": 1.286, + "args": { + "External id": 1432757,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569762.207, "dur": 3.460, + "args": { + "External id": 1432758,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569767.467, "dur": 0.923, + "args": { + "External id": 1432759,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569770.083, "dur": 1.500, + "args": { + "External id": 1432760,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851569773.163, "dur": 1.319, + "args": { + "External id": 1432761,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851569791.897, "dur": 152.362, + "args": { + "External id": 1432762,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851569808.894, "dur": 131.076, + "args": { + "External id": 1432763,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851569825.688, "dur": 16.724, + "args": { + "External id": 1432764,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851569846.651, "dur": 64.770, + "args": { + "External id": 1432765,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851569849.426, "dur": 61.657, + "args": { + "External id": 1432766,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851569853.843, "dur": 6.552, + "args": { + "External id": 1432767,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851569862.209, "dur": 48.243, + "args": { + "External id": 1432768,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2751 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 2338706, "tid": 2379422, + "ts": 6413851570133.619, "dur": 608.168, + "args": { + "External id": 1432769,"Record function id": 0, "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413851570154.692, "dur": 573.507, + "args": { + "External id": 1432770,"Record function id": 0, "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851570225.682, "dur": 6.651, + "args": { + "External id": 1432771,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851570248.966, "dur": 36.145, + "args": { + "External id": 1432772,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570254.984, "dur": 2.071, + "args": { + "External id": 1432773,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570259.794, "dur": 0.508, + "args": { + "External id": 1432774,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570262.127, "dur": 0.528, + "args": { + "External id": 1432775,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570264.702, "dur": 0.465, + "args": { + "External id": 1432776,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570266.782, "dur": 0.437, + "args": { + "External id": 1432777,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570269.145, "dur": 2.550, + "args": { + "External id": 1432778,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570273.502, "dur": 0.341, + "args": { + "External id": 1432779,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570275.769, "dur": 0.401, + "args": { + "External id": 1432780,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570278.237, "dur": 0.504, + "args": { + "External id": 1432781,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851570300.248, "dur": 47.235, + "args": { + "External id": 1432782,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851570380.188, "dur": 118.490, + "args": { + "External id": 1432783,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851570390.727, "dur": 4.099, + "args": { + "External id": 1432784,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851570400.339, "dur": 11.567, + "args": { + "External id": 1432785,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851570405.437, "dur": 5.994, + "args": { + "External id": 1432786,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570409.488, "dur": 0.671, + "args": { + "External id": 1432787,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851570418.977, "dur": 30.537, + "args": { + "External id": 1432788,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570421.177, "dur": 0.528, + "args": { + "External id": 1432789,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570423.821, "dur": 0.592, + "args": { + "External id": 1432790,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570426.458, "dur": 2.839, + "args": { + "External id": 1432791,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570431.435, "dur": 0.557, + "args": { + "External id": 1432792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570433.952, "dur": 0.462, + "args": { + "External id": 1432793,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570436.313, "dur": 0.388, + "args": { + "External id": 1432794,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570438.370, "dur": 0.371, + "args": { + "External id": 1432795,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570440.626, "dur": 0.493, + "args": { + "External id": 1432796,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851570442.912, "dur": 0.443, + "args": { + "External id": 1432797,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851570461.359, "dur": 29.023, + "args": { + "External id": 1432798,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851570546.298, "dur": 114.013, + "args": { + "External id": 1432799,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851570570.745, "dur": 86.258, + "args": { + "External id": 1432800,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2783, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851570580.760, "dur": 71.962, + "args": { + "External id": 1432801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851570674.492, "dur": 2.002, + "args": { + "External id": 1432802,"Record function id": 0, "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": 2785, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851570757.435, "dur": 1843.754, + "args": { + "External id": 1432803,"Sequence number": 15348696, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2786 + } + }, + { + "ph": "f", "id": 186, "pid": 2338706, "tid": 2379422, "ts": 6413851570757.435, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851570872.593, "dur": 122.308, + "args": { + "External id": 1432804,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851571040.157, "dur": 81.046, + "args": { + "External id": 1432805,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571146.436, "dur": 57.722, + "args": { + "External id": 1432806,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571217.384, "dur": 32.636, + "args": { + "External id": 1432807,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571257.718, "dur": 32.889, + "args": { + "External id": 1432808,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571298.691, "dur": 28.529, + "args": { + "External id": 1432809,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571335.457, "dur": 29.441, + "args": { + "External id": 1432810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851571393.952, "dur": 23.465, + "args": { + "External id": 1432811,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851571437.620, "dur": 30.452, + "args": { + "External id": 1432812,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851571491.606, "dur": 19.819, + "args": { + "External id": 1432813,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851571528.502, "dur": 15.854, + "args": { + "External id": 1432814,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571554.152, "dur": 38.742, + "args": { + "External id": 1432815,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851571596.539, "dur": 33.043, + "args": { + "External id": 1432816,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851571664.662, "dur": 261.610, + "args": { + "External id": 1432817,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851571751.775, "dur": 6.801, + "args": { + "External id": 1432818,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851571761.123, "dur": 3.589, + "args": { + "External id": 1432819,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851571766.236, "dur": 2.210, + "args": { + "External id": 1432820,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851571770.412, "dur": 2.310, + "args": { + "External id": 1432821,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851571820.203, "dur": 5.326, + "args": { + "External id": 1432822,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851571822.636, "dur": 2.704, + "args": { + "External id": 1432823,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851571828.358, "dur": 34.483, + "args": { + "External id": 1432824,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851571834.354, "dur": 3.797, + "args": { + "External id": 1432825,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851571864.716, "dur": 2.066, + "args": { + "External id": 1432826,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851571865.873, "dur": 0.823, + "args": { + "External id": 1432827,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851571868.060, "dur": 14.396, + "args": { + "External id": 1432828,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851571870.158, "dur": 0.523, + "args": { + "External id": 1432829,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851571965.338, "dur": 46.641, + "args": { + "External id": 1432830,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851572032.908, "dur": 17.496, + "args": { + "External id": 1432831,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851572095.605, "dur": 52.758, + "args": { + "External id": 1432832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851572156.391, "dur": 54.017, + "args": { + "External id": 1432833,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851572230.766, "dur": 26.883, + "args": { + "External id": 1432834,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851572264.860, "dur": 34.040, + "args": { + "External id": 1432835,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851572306.633, "dur": 30.960, + "args": { + "External id": 1432836,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851572345.763, "dur": 29.673, + "args": { + "External id": 1432837,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851572400.930, "dur": 28.071, + "args": { + "External id": 1432838,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851572445.821, "dur": 27.148, + "args": { + "External id": 1432839,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851572488.970, "dur": 18.793, + "args": { + "External id": 1432840,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851572526.041, "dur": 14.586, + "args": { + "External id": 1432841,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851572553.420, "dur": 16.310, + "args": { + "External id": 1432842,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572650.036, "dur": 17.065, + "args": { + "External id": 1432843,"Record function id": 0, "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572654.178, "dur": 12.060, + "args": { + "External id": 1432844,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572658.541, "dur": 6.768, + "args": { + "External id": 1432845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572660.571, "dur": 4.612, + "args": { + "External id": 1432846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572671.457, "dur": 6.551, + "args": { + "External id": 1432847,"Record function id": 0, "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572673.303, "dur": 4.197, + "args": { + "External id": 1432848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572674.313, "dur": 2.595, + "args": { + "External id": 1432849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572675.630, "dur": 1.205, + "args": { + "External id": 1432850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572681.639, "dur": 6.937, + "args": { + "External id": 1432851,"Record function id": 0, "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572682.927, "dur": 5.229, + "args": { + "External id": 1432852,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572683.650, "dur": 4.058, + "args": { + "External id": 1432853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572684.009, "dur": 3.613, + "args": { + "External id": 1432854,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572691.953, "dur": 4.537, + "args": { + "External id": 1432855,"Record function id": 0, "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572693.483, "dur": 2.591, + "args": { + "External id": 1432856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572694.057, "dur": 1.585, + "args": { + "External id": 1432857,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572694.656, "dur": 0.907, + "args": { + "External id": 1432858,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572700.202, "dur": 3.922, + "args": { + "External id": 1432859,"Record function id": 0, "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572701.369, "dur": 2.335, + "args": { + "External id": 1432860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572702.121, "dur": 1.006, + "args": { + "External id": 1432861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572702.505, "dur": 0.545, + "args": { + "External id": 1432862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572707.408, "dur": 4.087, + "args": { + "External id": 1432863,"Record function id": 0, "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572708.548, "dur": 2.541, + "args": { + "External id": 1432864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572709.152, "dur": 1.402, + "args": { + "External id": 1432865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572709.859, "dur": 0.585, + "args": { + "External id": 1432866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572714.882, "dur": 4.018, + "args": { + "External id": 1432867,"Record function id": 0, "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572716.093, "dur": 2.400, + "args": { + "External id": 1432868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572716.876, "dur": 1.179, + "args": { + "External id": 1432869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572717.354, "dur": 0.605, + "args": { + "External id": 1432870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572722.140, "dur": 3.747, + "args": { + "External id": 1432871,"Record function id": 0, "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572723.296, "dur": 2.162, + "args": { + "External id": 1432872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572723.755, "dur": 1.281, + "args": { + "External id": 1432873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572724.177, "dur": 0.793, + "args": { + "External id": 1432874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 2857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572729.320, "dur": 3.675, + "args": { + "External id": 1432875,"Record function id": 0, "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851572730.574, "dur": 2.015, + "args": { + "External id": 1432876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572731.103, "dur": 1.061, + "args": { + "External id": 1432877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851572731.482, "dur": 0.593, + "args": { + "External id": 1432878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 2861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851572737.353, "dur": 61699.236, + "args": { + "External id": 1432879,"Record function id": 0, "Sequence number": 15348695, "Fwd thread id": 1, "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851572739.305, "dur": 61687.171, + "args": { + "External id": 1432880,"Sequence number": 15348695, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2863 + } + }, + { + "ph": "f", "id": 187, "pid": 2338706, "tid": 2379422, "ts": 6413851572739.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413851572769.389, "dur": 38.286, + "args": { + "External id": 1432881,"Record function id": 0, "Ev Idx": 2864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413851572815.769, "dur": 66.156, + "args": { + "External id": 1432882,"Record function id": 0, "Ev Idx": 2865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413851572887.787, "dur": 61530.506, + "args": { + "External id": 1432883,"Record function id": 0, "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851572994.907, "dur": 8.537, + "args": { + "External id": 1432884,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851573016.326, "dur": 6.860, + "args": { + "External id": 1432885,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851573040.188, "dur": 60418.870, + "args": { + "External id": 1432886,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851573094.554, "dur": 60351.170, + "args": { + "External id": 1432887,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 2870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851573231.234, "dur": 19.964, + "args": { + "External id": 1432888,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851573271.695, "dur": 60125.634, + "args": { + "External id": 1432889,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 2872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851573274.923, "dur": 60121.336, + "args": { + "External id": 1432890,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 2873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851573280.153, "dur": 12.344, + "args": { + "External id": 1432891,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851573294.764, "dur": 60096.871, + "args": { + "External id": 1432892,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851633569.952, "dur": 13.425, + "args": { + "External id": 1432893,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 2876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851633574.120, "dur": 8.800, + "args": { + "External id": 1432894,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851633617.515, "dur": 466.929, + "args": { + "External id": 1432895,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 2878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851633647.591, "dur": 401.759, + "args": { + "External id": 1432896,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2879, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851633659.478, "dur": 382.890, + "args": { + "External id": 1432897,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 2880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851634109.438, "dur": 3.351, + "args": { + "External id": 1432898,"Record function id": 0, "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": 2881, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634183.056, "dur": 7.246, + "args": { + "External id": 1432899,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634240.652, "dur": 1.460, + "args": { + "External id": 1432900,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634261.593, "dur": 3.342, + "args": { + "External id": 1432901,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634279.268, "dur": 1.014, + "args": { + "External id": 1432902,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634293.456, "dur": 1.190, + "args": { + "External id": 1432903,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634307.092, "dur": 1.444, + "args": { + "External id": 1432904,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634322.249, "dur": 4.153, + "args": { + "External id": 1432905,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634339.760, "dur": 3.139, + "args": { + "External id": 1432906,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634355.220, "dur": 1.110, + "args": { + "External id": 1432907,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851634453.558, "dur": 3100.602, + "args": { + "External id": 1432908,"Record function id": 0, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413851634473.336, "dur": 1134.186, + "args": { + "External id": 1432909,"Record function id": 0, "Ev Idx": 2892 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413851634489.547, "dur": 357.561, + "args": { + "External id": 1432910,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634581.379, "dur": 4.359, + "args": { + "External id": 1432911,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634588.857, "dur": 1.263, + "args": { + "External id": 1432912,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634592.121, "dur": 3.568, + "args": { + "External id": 1432913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634597.329, "dur": 1.232, + "args": { + "External id": 1432914,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634600.011, "dur": 1.270, + "args": { + "External id": 1432915,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634603.009, "dur": 1.119, + "args": { + "External id": 1432916,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 2899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634605.968, "dur": 2.974, + "args": { + "External id": 1432917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 2900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634610.541, "dur": 1.041, + "args": { + "External id": 1432918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634613.156, "dur": 1.293, + "args": { + "External id": 1432919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851634616.094, "dur": 0.921, + "args": { + "External id": 1432920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 2903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851634657.509, "dur": 156.758, + "args": { + "External id": 1432921,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851634674.812, "dur": 134.551, + "args": { + "External id": 1432922,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 2905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851634693.384, "dur": 17.857, + "args": { + "External id": 1432923,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851634714.998, "dur": 65.299, + "args": { + "External id": 1432924,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 2907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851634717.850, "dur": 62.151, + "args": { + "External id": 1432925,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 2908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851634721.978, "dur": 5.286, + "args": { + "External id": 1432926,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851634729.300, "dur": 50.145, + "args": { + "External id": 1432927,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 2910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 2338706, "tid": 2379422, + "ts": 6413851634938.423, "dur": 660.699, + "args": { + "External id": 1432928,"Record function id": 0, "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413851634956.184, "dur": 629.324, + "args": { + "External id": 1432929,"Record function id": 0, "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851635042.057, "dur": 7.001, + "args": { + "External id": 1432930,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851635100.281, "dur": 37.665, + "args": { + "External id": 1432931,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635106.074, "dur": 1.760, + "args": { + "External id": 1432932,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635110.311, "dur": 0.635, + "args": { + "External id": 1432933,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635113.281, "dur": 0.469, + "args": { + "External id": 1432934,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635115.733, "dur": 0.854, + "args": { + "External id": 1432935,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635118.605, "dur": 0.406, + "args": { + "External id": 1432936,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635120.939, "dur": 2.246, + "args": { + "External id": 1432937,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635125.234, "dur": 0.465, + "args": { + "External id": 1432938,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635127.539, "dur": 0.389, + "args": { + "External id": 1432939,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635129.719, "dur": 0.660, + "args": { + "External id": 1432940,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851635149.931, "dur": 48.021, + "args": { + "External id": 1432941,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851635234.040, "dur": 122.841, + "args": { + "External id": 1432942,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 2925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851635245.643, "dur": 5.464, + "args": { + "External id": 1432943,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851635256.724, "dur": 10.738, + "args": { + "External id": 1432944,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851635261.234, "dur": 5.796, + "args": { + "External id": 1432945,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 2928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635265.154, "dur": 0.486, + "args": { + "External id": 1432946,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 2929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851635274.622, "dur": 31.817, + "args": { + "External id": 1432947,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 2930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635277.294, "dur": 0.584, + "args": { + "External id": 1432948,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635279.724, "dur": 0.555, + "args": { + "External id": 1432949,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635282.761, "dur": 2.603, + "args": { + "External id": 1432950,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635287.563, "dur": 0.778, + "args": { + "External id": 1432951,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635290.163, "dur": 0.383, + "args": { + "External id": 1432952,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635292.563, "dur": 0.579, + "args": { + "External id": 1432953,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635295.270, "dur": 0.600, + "args": { + "External id": 1432954,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635297.786, "dur": 0.522, + "args": { + "External id": 1432955,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851635300.163, "dur": 0.582, + "args": { + "External id": 1432956,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 2939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851635316.575, "dur": 32.302, + "args": { + "External id": 1432957,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851635405.555, "dur": 112.375, + "args": { + "External id": 1432958,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851635429.147, "dur": 85.196, + "args": { + "External id": 1432959,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2942, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851635439.014, "dur": 70.634, + "args": { + "External id": 1432960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 2943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851635531.530, "dur": 1.955, + "args": { + "External id": 1432961,"Record function id": 0, "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": 2944, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851635615.497, "dur": 1911.406, + "args": { + "External id": 1432962,"Sequence number": 15348694, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 2945 + } + }, + { + "ph": "f", "id": 188, "pid": 2338706, "tid": 2379422, "ts": 6413851635615.497, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851635728.737, "dur": 103.802, + "args": { + "External id": 1432963,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 2946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851635872.493, "dur": 41.798, + "args": { + "External id": 1432964,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 2947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851635934.581, "dur": 71.894, + "args": { + "External id": 1432965,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 2948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636022.979, "dur": 74.074, + "args": { + "External id": 1432966,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636109.464, "dur": 40.052, + "args": { + "External id": 1432967,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636157.768, "dur": 30.391, + "args": { + "External id": 1432968,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 2951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636197.375, "dur": 29.912, + "args": { + "External id": 1432969,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 2952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851636256.199, "dur": 27.785, + "args": { + "External id": 1432970,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 2953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851636325.223, "dur": 28.862, + "args": { + "External id": 1432971,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851636378.506, "dur": 22.548, + "args": { + "External id": 1432972,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851636415.758, "dur": 15.478, + "args": { + "External id": 1432973,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636441.946, "dur": 40.343, + "args": { + "External id": 1432974,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636486.349, "dur": 34.232, + "args": { + "External id": 1432975,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851636555.345, "dur": 286.096, + "args": { + "External id": 1432976,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851636636.059, "dur": 6.121, + "args": { + "External id": 1432977,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851636644.322, "dur": 3.094, + "args": { + "External id": 1432978,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851636673.500, "dur": 2.489, + "args": { + "External id": 1432979,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851636677.902, "dur": 2.278, + "args": { + "External id": 1432980,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851636728.610, "dur": 5.246, + "args": { + "External id": 1432981,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851636730.989, "dur": 2.656, + "args": { + "External id": 1432982,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851636736.550, "dur": 36.490, + "args": { + "External id": 1432983,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851636742.606, "dur": 4.199, + "args": { + "External id": 1432984,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851636774.928, "dur": 2.239, + "args": { + "External id": 1432985,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851636776.194, "dur": 0.885, + "args": { + "External id": 1432986,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 2969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851636778.714, "dur": 15.218, + "args": { + "External id": 1432987,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 2970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851636781.030, "dur": 0.819, + "args": { + "External id": 1432988,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 2971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851636882.124, "dur": 27.475, + "args": { + "External id": 1432989,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851636926.692, "dur": 16.824, + "args": { + "External id": 1432990,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851636952.918, "dur": 64.902, + "args": { + "External id": 1432991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851637044.910, "dur": 94.765, + "args": { + "External id": 1432992,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851637159.705, "dur": 25.667, + "args": { + "External id": 1432993,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 2976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851637196.111, "dur": 31.090, + "args": { + "External id": 1432994,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 2977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851637236.039, "dur": 31.931, + "args": { + "External id": 1432995,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 2978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851637276.960, "dur": 30.646, + "args": { + "External id": 1432996,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 2979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851637331.130, "dur": 27.916, + "args": { + "External id": 1432997,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 2980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851637375.180, "dur": 25.183, + "args": { + "External id": 1432998,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851637416.013, "dur": 17.528, + "args": { + "External id": 1432999,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 2982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851637451.145, "dur": 14.118, + "args": { + "External id": 1433000,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 2983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851637477.807, "dur": 16.281, + "args": { + "External id": 1433001,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 2984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637577.470, "dur": 16.167, + "args": { + "External id": 1433002,"Record function id": 0, "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637580.988, "dur": 11.622, + "args": { + "External id": 1433003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637585.542, "dur": 6.095, + "args": { + "External id": 1433004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637587.380, "dur": 4.104, + "args": { + "External id": 1433005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637597.903, "dur": 5.463, + "args": { + "External id": 1433006,"Record function id": 0, "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637599.428, "dur": 3.498, + "args": { + "External id": 1433007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637600.209, "dur": 2.126, + "args": { + "External id": 1433008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637601.088, "dur": 1.143, + "args": { + "External id": 1433009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 2992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637606.815, "dur": 7.831, + "args": { + "External id": 1433010,"Record function id": 0, "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637608.090, "dur": 6.136, + "args": { + "External id": 1433011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637608.964, "dur": 4.848, + "args": { + "External id": 1433012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637609.354, "dur": 4.390, + "args": { + "External id": 1433013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 2996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637618.168, "dur": 4.295, + "args": { + "External id": 1433014,"Record function id": 0, "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637619.626, "dur": 2.424, + "args": { + "External id": 1433015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637620.268, "dur": 1.388, + "args": { + "External id": 1433016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 2999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637620.573, "dur": 1.015, + "args": { + "External id": 1433017,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637625.748, "dur": 30.092, + "args": { + "External id": 1433018,"Record function id": 0, "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637627.014, "dur": 27.772, + "args": { + "External id": 1433019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637650.813, "dur": 3.062, + "args": { + "External id": 1433020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637652.111, "dur": 1.491, + "args": { + "External id": 1433021,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637661.421, "dur": 5.521, + "args": { + "External id": 1433022,"Record function id": 0, "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637663.199, "dur": 3.294, + "args": { + "External id": 1433023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637664.280, "dur": 1.628, + "args": { + "External id": 1433024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637664.909, "dur": 0.880, + "args": { + "External id": 1433025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637670.364, "dur": 4.530, + "args": { + "External id": 1433026,"Record function id": 0, "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637671.780, "dur": 2.699, + "args": { + "External id": 1433027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637672.775, "dur": 1.287, + "args": { + "External id": 1433028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637673.263, "dur": 0.683, + "args": { + "External id": 1433029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637678.335, "dur": 4.079, + "args": { + "External id": 1433030,"Record function id": 0, "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637679.737, "dur": 2.260, + "args": { + "External id": 1433031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637680.342, "dur": 1.167, + "args": { + "External id": 1433032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637680.764, "dur": 0.678, + "args": { + "External id": 1433033,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637685.706, "dur": 4.643, + "args": { + "External id": 1433034,"Record function id": 0, "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851637687.065, "dur": 2.862, + "args": { + "External id": 1433035,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637687.859, "dur": 1.451, + "args": { + "External id": 1433036,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851637688.482, "dur": 0.740, + "args": { + "External id": 1433037,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851637694.640, "dur": 62812.894, + "args": { + "External id": 1433038,"Record function id": 0, "Sequence number": 15348693, "Fwd thread id": 1, "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851637696.176, "dur": 62801.939, + "args": { + "External id": 1433039,"Sequence number": 15348693, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3022 + } + }, + { + "ph": "f", "id": 189, "pid": 2338706, "tid": 2379422, "ts": 6413851637696.176, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413851637729.210, "dur": 41.916, + "args": { + "External id": 1433040,"Record function id": 0, "Ev Idx": 3023 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413851637779.256, "dur": 69.034, + "args": { + "External id": 1433041,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413851637854.183, "dur": 62635.383, + "args": { + "External id": 1433042,"Record function id": 0, "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851637948.149, "dur": 7.777, + "args": { + "External id": 1433043,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851637965.851, "dur": 6.716, + "args": { + "External id": 1433044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851638002.733, "dur": 61620.150, + "args": { + "External id": 1433045,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851638017.414, "dur": 61591.458, + "args": { + "External id": 1433046,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851638163.827, "dur": 21.470, + "args": { + "External id": 1433047,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851638205.812, "dur": 61356.101, + "args": { + "External id": 1433048,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851638209.327, "dur": 61351.511, + "args": { + "External id": 1433049,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851638214.617, "dur": 11.384, + "args": { + "External id": 1433050,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851638228.322, "dur": 61327.039, + "args": { + "External id": 1433051,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851699739.288, "dur": 13.707, + "args": { + "External id": 1433052,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851699743.447, "dur": 9.115, + "args": { + "External id": 1433053,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851699786.241, "dur": 373.099, + "args": { + "External id": 1433054,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851699815.234, "dur": 337.983, + "args": { + "External id": 1433055,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3038, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851699827.038, "dur": 319.967, + "args": { + "External id": 1433056,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851700182.378, "dur": 2.334, + "args": { + "External id": 1433057,"Record function id": 0, "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": 3040, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700252.024, "dur": 7.075, + "args": { + "External id": 1433058,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700307.727, "dur": 1.793, + "args": { + "External id": 1433059,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700327.493, "dur": 3.667, + "args": { + "External id": 1433060,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700345.501, "dur": 1.013, + "args": { + "External id": 1433061,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700360.780, "dur": 0.833, + "args": { + "External id": 1433062,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700374.886, "dur": 0.930, + "args": { + "External id": 1433063,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700389.804, "dur": 3.195, + "args": { + "External id": 1433064,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700406.418, "dur": 3.022, + "args": { + "External id": 1433065,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700422.768, "dur": 0.869, + "args": { + "External id": 1433066,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851700522.946, "dur": 3269.211, + "args": { + "External id": 1433067,"Record function id": 0, "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413851700544.089, "dur": 1283.091, + "args": { + "External id": 1433068,"Record function id": 0, "Ev Idx": 3051 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413851700560.773, "dur": 365.846, + "args": { + "External id": 1433069,"Record function id": 0, "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700657.529, "dur": 4.418, + "args": { + "External id": 1433070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700665.174, "dur": 0.879, + "args": { + "External id": 1433071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700668.121, "dur": 3.569, + "args": { + "External id": 1433072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700673.353, "dur": 0.906, + "args": { + "External id": 1433073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700675.719, "dur": 1.256, + "args": { + "External id": 1433074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700678.923, "dur": 1.027, + "args": { + "External id": 1433075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700681.601, "dur": 1.949, + "args": { + "External id": 1433076,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700685.320, "dur": 0.807, + "args": { + "External id": 1433077,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700687.798, "dur": 1.023, + "args": { + "External id": 1433078,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851700690.635, "dur": 1.003, + "args": { + "External id": 1433079,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851700735.406, "dur": 157.273, + "args": { + "External id": 1433080,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851700752.181, "dur": 135.958, + "args": { + "External id": 1433081,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851700770.877, "dur": 18.497, + "args": { + "External id": 1433082,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851700793.223, "dur": 65.084, + "args": { + "External id": 1433083,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851700796.102, "dur": 61.875, + "args": { + "External id": 1433084,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851700800.318, "dur": 5.678, + "args": { + "External id": 1433085,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851700808.101, "dur": 49.266, + "args": { + "External id": 1433086,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 2338706, "tid": 2379422, + "ts": 6413851701050.837, "dur": 767.149, + "args": { + "External id": 1433087,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413851701109.983, "dur": 693.571, + "args": { + "External id": 1433088,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851701275.857, "dur": 17.703, + "args": { + "External id": 1433089,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851701312.623, "dur": 34.368, + "args": { + "External id": 1433090,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701318.468, "dur": 2.059, + "args": { + "External id": 1433091,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701322.913, "dur": 0.559, + "args": { + "External id": 1433092,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701325.278, "dur": 0.658, + "args": { + "External id": 1433093,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701327.688, "dur": 0.420, + "args": { + "External id": 1433094,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701329.731, "dur": 0.645, + "args": { + "External id": 1433095,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701332.158, "dur": 2.158, + "args": { + "External id": 1433096,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701335.901, "dur": 0.641, + "args": { + "External id": 1433097,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701338.361, "dur": 0.423, + "args": { + "External id": 1433098,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701340.304, "dur": 0.476, + "args": { + "External id": 1433099,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851701358.803, "dur": 54.757, + "args": { + "External id": 1433100,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851701448.909, "dur": 118.458, + "args": { + "External id": 1433101,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851701460.203, "dur": 4.522, + "args": { + "External id": 1433102,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851701470.190, "dur": 11.556, + "args": { + "External id": 1433103,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851701474.747, "dur": 6.539, + "args": { + "External id": 1433104,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701479.337, "dur": 0.833, + "args": { + "External id": 1433105,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851701488.814, "dur": 27.718, + "args": { + "External id": 1433106,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701491.255, "dur": 0.476, + "args": { + "External id": 1433107,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701493.490, "dur": 0.420, + "args": { + "External id": 1433108,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701495.760, "dur": 2.591, + "args": { + "External id": 1433109,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701500.094, "dur": 0.429, + "args": { + "External id": 1433110,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701502.292, "dur": 0.431, + "args": { + "External id": 1433111,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701504.428, "dur": 0.404, + "args": { + "External id": 1433112,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701506.617, "dur": 0.441, + "args": { + "External id": 1433113,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701508.697, "dur": 0.350, + "args": { + "External id": 1433114,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851701510.980, "dur": 0.405, + "args": { + "External id": 1433115,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851701529.352, "dur": 29.684, + "args": { + "External id": 1433116,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851701619.607, "dur": 114.872, + "args": { + "External id": 1433117,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851701644.301, "dur": 86.416, + "args": { + "External id": 1433118,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3101, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851701654.379, "dur": 71.844, + "args": { + "External id": 1433119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851701748.455, "dur": 1.748, + "args": { + "External id": 1433120,"Record function id": 0, "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": 3103, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851701835.727, "dur": 1929.904, + "args": { + "External id": 1433121,"Sequence number": 15348692, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3104 + } + }, + { + "ph": "f", "id": 190, "pid": 2338706, "tid": 2379422, "ts": 6413851701835.727, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851701952.667, "dur": 163.707, + "args": { + "External id": 1433122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851702213.927, "dur": 45.730, + "args": { + "External id": 1433123,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702282.492, "dur": 62.469, + "args": { + "External id": 1433124,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702358.532, "dur": 35.705, + "args": { + "External id": 1433125,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702402.306, "dur": 34.023, + "args": { + "External id": 1433126,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702443.672, "dur": 29.628, + "args": { + "External id": 1433127,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702481.826, "dur": 30.251, + "args": { + "External id": 1433128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851702538.635, "dur": 24.794, + "args": { + "External id": 1433129,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851702582.199, "dur": 28.475, + "args": { + "External id": 1433130,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851702631.824, "dur": 25.947, + "args": { + "External id": 1433131,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851702671.252, "dur": 16.008, + "args": { + "External id": 1433132,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702696.840, "dur": 40.475, + "args": { + "External id": 1433133,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851702741.097, "dur": 33.641, + "args": { + "External id": 1433134,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851702809.449, "dur": 335.884, + "args": { + "External id": 1433135,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851702893.363, "dur": 6.343, + "args": { + "External id": 1433136,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851702901.834, "dur": 3.219, + "args": { + "External id": 1433137,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851702906.615, "dur": 2.089, + "args": { + "External id": 1433138,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851702910.200, "dur": 2.213, + "args": { + "External id": 1433139,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851702961.991, "dur": 4.972, + "args": { + "External id": 1433140,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851702963.902, "dur": 2.910, + "args": { + "External id": 1433141,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851702969.547, "dur": 61.035, + "args": { + "External id": 1433142,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851702993.677, "dur": 4.452, + "args": { + "External id": 1433143,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851703033.321, "dur": 2.165, + "args": { + "External id": 1433144,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851703034.462, "dur": 0.929, + "args": { + "External id": 1433145,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851703036.981, "dur": 55.399, + "args": { + "External id": 1433146,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851703039.325, "dur": 0.646, + "args": { + "External id": 1433147,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851703190.010, "dur": 33.903, + "args": { + "External id": 1433148,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851703241.032, "dur": 36.591, + "args": { + "External id": 1433149,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851703293.053, "dur": 53.389, + "args": { + "External id": 1433150,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851703353.434, "dur": 44.365, + "args": { + "External id": 1433151,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851703408.821, "dur": 22.807, + "args": { + "External id": 1433152,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851703437.931, "dur": 35.978, + "args": { + "External id": 1433153,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851703481.735, "dur": 29.612, + "args": { + "External id": 1433154,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851703518.938, "dur": 30.427, + "args": { + "External id": 1433155,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851703568.707, "dur": 25.373, + "args": { + "External id": 1433156,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851703609.485, "dur": 26.085, + "args": { + "External id": 1433157,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851703650.660, "dur": 18.999, + "args": { + "External id": 1433158,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851703686.339, "dur": 15.846, + "args": { + "External id": 1433159,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851703715.386, "dur": 18.026, + "args": { + "External id": 1433160,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703815.535, "dur": 16.499, + "args": { + "External id": 1433161,"Record function id": 0, "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703819.511, "dur": 11.585, + "args": { + "External id": 1433162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703823.901, "dur": 6.177, + "args": { + "External id": 1433163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703825.864, "dur": 4.093, + "args": { + "External id": 1433164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703835.925, "dur": 28.740, + "args": { + "External id": 1433165,"Record function id": 0, "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703837.646, "dur": 26.463, + "args": { + "External id": 1433166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703838.501, "dur": 24.897, + "args": { + "External id": 1433167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703862.138, "dur": 1.156, + "args": { + "External id": 1433168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703868.259, "dur": 7.308, + "args": { + "External id": 1433169,"Record function id": 0, "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703869.893, "dur": 5.167, + "args": { + "External id": 1433170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703870.467, "dur": 4.025, + "args": { + "External id": 1433171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703870.748, "dur": 3.673, + "args": { + "External id": 1433172,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703878.956, "dur": 4.222, + "args": { + "External id": 1433173,"Record function id": 0, "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703880.277, "dur": 2.480, + "args": { + "External id": 1433174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703880.934, "dur": 1.387, + "args": { + "External id": 1433175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703881.392, "dur": 0.862, + "args": { + "External id": 1433176,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703886.493, "dur": 4.425, + "args": { + "External id": 1433177,"Record function id": 0, "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703887.777, "dur": 2.721, + "args": { + "External id": 1433178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703888.616, "dur": 1.427, + "args": { + "External id": 1433179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703889.129, "dur": 0.841, + "args": { + "External id": 1433180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703894.278, "dur": 4.528, + "args": { + "External id": 1433181,"Record function id": 0, "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703895.892, "dur": 2.508, + "args": { + "External id": 1433182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703896.510, "dur": 1.342, + "args": { + "External id": 1433183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703897.178, "dur": 0.587, + "args": { + "External id": 1433184,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703902.125, "dur": 6.307, + "args": { + "External id": 1433185,"Record function id": 0, "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703903.757, "dur": 4.220, + "args": { + "External id": 1433186,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703904.218, "dur": 3.150, + "args": { + "External id": 1433187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703906.644, "dur": 0.651, + "args": { + "External id": 1433188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703911.665, "dur": 4.281, + "args": { + "External id": 1433189,"Record function id": 0, "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703913.191, "dur": 2.334, + "args": { + "External id": 1433190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703913.866, "dur": 1.050, + "args": { + "External id": 1433191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703914.150, "dur": 0.646, + "args": { + "External id": 1433192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703919.063, "dur": 3.891, + "args": { + "External id": 1433193,"Record function id": 0, "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851703920.282, "dur": 2.237, + "args": { + "External id": 1433194,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703920.749, "dur": 1.311, + "args": { + "External id": 1433195,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851703921.145, "dur": 0.840, + "args": { + "External id": 1433196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851703926.991, "dur": 63362.843, + "args": { + "External id": 1433197,"Record function id": 0, "Sequence number": 15348691, "Fwd thread id": 1, "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851703928.415, "dur": 63351.725, + "args": { + "External id": 1433198,"Sequence number": 15348691, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3181 + } + }, + { + "ph": "f", "id": 191, "pid": 2338706, "tid": 2379422, "ts": 6413851703928.415, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413851703961.081, "dur": 60.080, + "args": { + "External id": 1433199,"Record function id": 0, "Ev Idx": 3182 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413851704030.177, "dur": 107.407, + "args": { + "External id": 1433200,"Record function id": 0, "Ev Idx": 3183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413851704145.442, "dur": 63125.503, + "args": { + "External id": 1433201,"Record function id": 0, "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851704241.600, "dur": 7.610, + "args": { + "External id": 1433202,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851704259.571, "dur": 7.047, + "args": { + "External id": 1433203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851704282.634, "dur": 62082.767, + "args": { + "External id": 1433204,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851704297.815, "dur": 62054.234, + "args": { + "External id": 1433205,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851704392.281, "dur": 17.941, + "args": { + "External id": 1433206,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851704430.118, "dur": 61873.614, + "args": { + "External id": 1433207,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851704433.457, "dur": 61869.197, + "args": { + "External id": 1433208,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851704438.042, "dur": 9.271, + "args": { + "External id": 1433209,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851704450.037, "dur": 61847.844, + "args": { + "External id": 1433210,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851766479.881, "dur": 13.250, + "args": { + "External id": 1433211,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851766483.878, "dur": 8.861, + "args": { + "External id": 1433212,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851766526.235, "dur": 375.546, + "args": { + "External id": 1433213,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851766555.509, "dur": 341.357, + "args": { + "External id": 1433214,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3197, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851766567.366, "dur": 324.226, + "args": { + "External id": 1433215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851766920.691, "dur": 2.144, + "args": { + "External id": 1433216,"Record function id": 0, "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": 3199, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767001.358, "dur": 7.374, + "args": { + "External id": 1433217,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767091.295, "dur": 2.524, + "args": { + "External id": 1433218,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767116.008, "dur": 3.109, + "args": { + "External id": 1433219,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767133.043, "dur": 1.055, + "args": { + "External id": 1433220,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767147.122, "dur": 0.866, + "args": { + "External id": 1433221,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767160.810, "dur": 1.225, + "args": { + "External id": 1433222,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767173.501, "dur": 3.369, + "args": { + "External id": 1433223,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767189.580, "dur": 2.746, + "args": { + "External id": 1433224,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767205.423, "dur": 1.130, + "args": { + "External id": 1433225,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851767306.861, "dur": 3078.954, + "args": { + "External id": 1433226,"Record function id": 0, "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413851767327.717, "dur": 1158.610, + "args": { + "External id": 1433227,"Record function id": 0, "Ev Idx": 3210 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413851767344.610, "dur": 368.777, + "args": { + "External id": 1433228,"Record function id": 0, "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767441.617, "dur": 4.176, + "args": { + "External id": 1433229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767449.244, "dur": 0.960, + "args": { + "External id": 1433230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767452.316, "dur": 3.145, + "args": { + "External id": 1433231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767457.074, "dur": 1.063, + "args": { + "External id": 1433232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767459.782, "dur": 0.882, + "args": { + "External id": 1433233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767462.602, "dur": 0.940, + "args": { + "External id": 1433234,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767465.467, "dur": 1.695, + "args": { + "External id": 1433235,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767469.093, "dur": 0.722, + "args": { + "External id": 1433236,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767471.290, "dur": 1.329, + "args": { + "External id": 1433237,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851767474.268, "dur": 0.842, + "args": { + "External id": 1433238,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851767493.213, "dur": 185.500, + "args": { + "External id": 1433239,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851767534.131, "dur": 139.428, + "args": { + "External id": 1433240,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851767553.235, "dur": 19.249, + "args": { + "External id": 1433241,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851767576.474, "dur": 66.301, + "args": { + "External id": 1433242,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851767579.436, "dur": 62.965, + "args": { + "External id": 1433243,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767583.860, "dur": 5.281, + "args": { + "External id": 1433244,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851767591.206, "dur": 50.486, + "args": { + "External id": 1433245,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3228 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 2338706, "tid": 2379422, + "ts": 6413851767809.941, "dur": 667.815, + "args": { + "External id": 1433246,"Record function id": 0, "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413851767828.733, "dur": 635.180, + "args": { + "External id": 1433247,"Record function id": 0, "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851767893.172, "dur": 5.220, + "args": { + "External id": 1433248,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851767914.105, "dur": 33.415, + "args": { + "External id": 1433249,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767919.373, "dur": 1.689, + "args": { + "External id": 1433250,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767923.886, "dur": 0.665, + "args": { + "External id": 1433251,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767926.320, "dur": 0.424, + "args": { + "External id": 1433252,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767928.809, "dur": 0.424, + "args": { + "External id": 1433253,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767931.300, "dur": 0.455, + "args": { + "External id": 1433254,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767933.715, "dur": 2.053, + "args": { + "External id": 1433255,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767937.805, "dur": 0.438, + "args": { + "External id": 1433256,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767940.537, "dur": 0.553, + "args": { + "External id": 1433257,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851767942.804, "dur": 0.322, + "args": { + "External id": 1433258,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851767958.433, "dur": 64.258, + "args": { + "External id": 1433259,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851768093.860, "dur": 133.088, + "args": { + "External id": 1433260,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851768106.558, "dur": 5.678, + "args": { + "External id": 1433261,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851768119.245, "dur": 12.641, + "args": { + "External id": 1433262,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851768124.288, "dur": 7.166, + "args": { + "External id": 1433263,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768128.851, "dur": 0.759, + "args": { + "External id": 1433264,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851768139.528, "dur": 31.195, + "args": { + "External id": 1433265,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768142.331, "dur": 0.414, + "args": { + "External id": 1433266,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768148.060, "dur": 0.442, + "args": { + "External id": 1433267,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768150.349, "dur": 2.807, + "args": { + "External id": 1433268,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768154.993, "dur": 0.439, + "args": { + "External id": 1433269,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768157.177, "dur": 0.574, + "args": { + "External id": 1433270,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768159.545, "dur": 0.392, + "args": { + "External id": 1433271,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768161.622, "dur": 0.327, + "args": { + "External id": 1433272,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768163.704, "dur": 0.443, + "args": { + "External id": 1433273,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851768165.929, "dur": 0.372, + "args": { + "External id": 1433274,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851768182.164, "dur": 36.729, + "args": { + "External id": 1433275,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851768278.593, "dur": 115.376, + "args": { + "External id": 1433276,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851768301.797, "dur": 88.665, + "args": { + "External id": 1433277,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3260, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851768312.130, "dur": 74.037, + "args": { + "External id": 1433278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851768408.327, "dur": 1.815, + "args": { + "External id": 1433279,"Record function id": 0, "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": 3262, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851768494.392, "dur": 1864.660, + "args": { + "External id": 1433280,"Sequence number": 15348690, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3263 + } + }, + { + "ph": "f", "id": 192, "pid": 2338706, "tid": 2379422, "ts": 6413851768494.392, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851768607.550, "dur": 104.344, + "args": { + "External id": 1433281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851768752.193, "dur": 41.563, + "args": { + "External id": 1433282,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851768812.248, "dur": 49.014, + "args": { + "External id": 1433283,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851768874.026, "dur": 33.409, + "args": { + "External id": 1433284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851768914.638, "dur": 34.313, + "args": { + "External id": 1433285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851768956.343, "dur": 54.938, + "args": { + "External id": 1433286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769021.537, "dur": 71.806, + "args": { + "External id": 1433287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851769125.948, "dur": 26.220, + "args": { + "External id": 1433288,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851769172.072, "dur": 28.801, + "args": { + "External id": 1433289,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851769222.111, "dur": 19.489, + "args": { + "External id": 1433290,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851769254.924, "dur": 14.402, + "args": { + "External id": 1433291,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769279.443, "dur": 41.116, + "args": { + "External id": 1433292,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769324.788, "dur": 32.660, + "args": { + "External id": 1433293,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851769389.970, "dur": 255.034, + "args": { + "External id": 1433294,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851769476.180, "dur": 6.069, + "args": { + "External id": 1433295,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851769484.498, "dur": 2.794, + "args": { + "External id": 1433296,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851769488.970, "dur": 2.039, + "args": { + "External id": 1433297,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851769492.242, "dur": 1.654, + "args": { + "External id": 1433298,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851769539.149, "dur": 5.067, + "args": { + "External id": 1433299,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851769541.139, "dur": 2.858, + "args": { + "External id": 1433300,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851769546.336, "dur": 32.974, + "args": { + "External id": 1433301,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851769551.702, "dur": 3.757, + "args": { + "External id": 1433302,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851769581.199, "dur": 2.426, + "args": { + "External id": 1433303,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851769582.648, "dur": 0.887, + "args": { + "External id": 1433304,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851769585.309, "dur": 14.800, + "args": { + "External id": 1433305,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851769587.412, "dur": 0.795, + "args": { + "External id": 1433306,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851769682.322, "dur": 26.756, + "args": { + "External id": 1433307,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851769726.083, "dur": 16.317, + "args": { + "External id": 1433308,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769751.422, "dur": 43.482, + "args": { + "External id": 1433309,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769802.394, "dur": 41.040, + "args": { + "External id": 1433310,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769853.763, "dur": 23.163, + "args": { + "External id": 1433311,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769883.891, "dur": 32.358, + "args": { + "External id": 1433312,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851769924.680, "dur": 68.611, + "args": { + "External id": 1433313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851770018.083, "dur": 94.841, + "args": { + "External id": 1433314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851770141.088, "dur": 32.687, + "args": { + "External id": 1433315,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851770190.402, "dur": 27.918, + "args": { + "External id": 1433316,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851770237.098, "dur": 19.476, + "args": { + "External id": 1433317,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851770274.476, "dur": 20.915, + "args": { + "External id": 1433318,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851770308.860, "dur": 17.348, + "args": { + "External id": 1433319,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770408.577, "dur": 15.867, + "args": { + "External id": 1433320,"Record function id": 0, "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770411.993, "dur": 11.455, + "args": { + "External id": 1433321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770416.354, "dur": 6.153, + "args": { + "External id": 1433322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770418.122, "dur": 4.219, + "args": { + "External id": 1433323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770428.483, "dur": 5.593, + "args": { + "External id": 1433324,"Record function id": 0, "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770429.914, "dur": 3.717, + "args": { + "External id": 1433325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770430.664, "dur": 2.301, + "args": { + "External id": 1433326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770431.590, "dur": 1.269, + "args": { + "External id": 1433327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770437.530, "dur": 6.522, + "args": { + "External id": 1433328,"Record function id": 0, "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770438.880, "dur": 4.741, + "args": { + "External id": 1433329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770439.378, "dur": 3.772, + "args": { + "External id": 1433330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770439.671, "dur": 3.409, + "args": { + "External id": 1433331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770447.394, "dur": 4.062, + "args": { + "External id": 1433332,"Record function id": 0, "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770448.411, "dur": 2.592, + "args": { + "External id": 1433333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770449.060, "dur": 1.400, + "args": { + "External id": 1433334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770449.692, "dur": 0.701, + "args": { + "External id": 1433335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770454.946, "dur": 3.884, + "args": { + "External id": 1433336,"Record function id": 0, "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770456.078, "dur": 2.322, + "args": { + "External id": 1433337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770456.569, "dur": 1.389, + "args": { + "External id": 1433338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770457.048, "dur": 0.845, + "args": { + "External id": 1433339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770462.188, "dur": 3.983, + "args": { + "External id": 1433340,"Record function id": 0, "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770463.370, "dur": 2.352, + "args": { + "External id": 1433341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770463.978, "dur": 1.302, + "args": { + "External id": 1433342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770464.631, "dur": 0.540, + "args": { + "External id": 1433343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770469.431, "dur": 3.482, + "args": { + "External id": 1433344,"Record function id": 0, "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770470.538, "dur": 1.954, + "args": { + "External id": 1433345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770471.011, "dur": 0.958, + "args": { + "External id": 1433346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770471.300, "dur": 0.588, + "args": { + "External id": 1433347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770476.218, "dur": 3.827, + "args": { + "External id": 1433348,"Record function id": 0, "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770477.378, "dur": 2.251, + "args": { + "External id": 1433349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770477.858, "dur": 1.345, + "args": { + "External id": 1433350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770478.434, "dur": 0.704, + "args": { + "External id": 1433351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770483.330, "dur": 4.608, + "args": { + "External id": 1433352,"Record function id": 0, "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851770484.773, "dur": 2.765, + "args": { + "External id": 1433353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770485.638, "dur": 1.247, + "args": { + "External id": 1433354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851770486.167, "dur": 0.631, + "args": { + "External id": 1433355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851770491.753, "dur": 61282.901, + "args": { + "External id": 1433356,"Record function id": 0, "Sequence number": 15348689, "Fwd thread id": 1, "Ev Idx": 3339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851770493.433, "dur": 61271.918, + "args": { + "External id": 1433357,"Sequence number": 15348689, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3340 + } + }, + { + "ph": "f", "id": 193, "pid": 2338706, "tid": 2379422, "ts": 6413851770493.433, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413851770522.779, "dur": 40.153, + "args": { + "External id": 1433358,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413851770570.550, "dur": 66.289, + "args": { + "External id": 1433359,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413851770642.472, "dur": 61115.140, + "args": { + "External id": 1433360,"Record function id": 0, "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851770734.022, "dur": 6.833, + "args": { + "External id": 1433361,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851770751.098, "dur": 6.743, + "args": { + "External id": 1433362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851770773.054, "dur": 60026.081, + "args": { + "External id": 1433363,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851770787.345, "dur": 59998.235, + "args": { + "External id": 1433364,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851770920.236, "dur": 17.579, + "args": { + "External id": 1433365,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851770957.790, "dur": 59779.143, + "args": { + "External id": 1433366,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851770960.964, "dur": 59774.901, + "args": { + "External id": 1433367,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851770965.361, "dur": 29.811, + "args": { + "External id": 1433368,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851770998.650, "dur": 59732.040, + "args": { + "External id": 1433369,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851830910.875, "dur": 14.030, + "args": { + "External id": 1433370,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851830915.183, "dur": 9.327, + "args": { + "External id": 1433371,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851830958.850, "dur": 468.341, + "args": { + "External id": 1433372,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851831002.195, "dur": 418.494, + "args": { + "External id": 1433373,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3356, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851831015.595, "dur": 399.046, + "args": { + "External id": 1433374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851831449.533, "dur": 2.648, + "args": { + "External id": 1433375,"Record function id": 0, "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": 3358, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831523.577, "dur": 7.150, + "args": { + "External id": 1433376,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831580.214, "dur": 1.662, + "args": { + "External id": 1433377,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831599.348, "dur": 3.606, + "args": { + "External id": 1433378,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831616.303, "dur": 1.053, + "args": { + "External id": 1433379,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831628.561, "dur": 1.143, + "args": { + "External id": 1433380,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831641.186, "dur": 1.008, + "args": { + "External id": 1433381,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831653.472, "dur": 3.159, + "args": { + "External id": 1433382,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831676.090, "dur": 3.104, + "args": { + "External id": 1433383,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851831691.678, "dur": 1.465, + "args": { + "External id": 1433384,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851831789.474, "dur": 3004.393, + "args": { + "External id": 1433385,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413851831809.943, "dur": 1150.181, + "args": { + "External id": 1433386,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413851831825.287, "dur": 408.961, + "args": { + "External id": 1433387,"Record function id": 0, "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831921.234, "dur": 4.426, + "args": { + "External id": 1433388,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831928.636, "dur": 0.943, + "args": { + "External id": 1433389,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831931.452, "dur": 3.913, + "args": { + "External id": 1433390,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831937.099, "dur": 1.175, + "args": { + "External id": 1433391,"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": 2338706, "tid": 2379422, + "ts": 6413851831939.830, "dur": 1.550, + "args": { + "External id": 1433392,"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": 2338706, "tid": 2379422, + "ts": 6413851831943.090, "dur": 0.794, + "args": { + "External id": 1433393,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831945.392, "dur": 3.142, + "args": { + "External id": 1433394,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831949.853, "dur": 0.949, + "args": { + "External id": 1433395,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831952.120, "dur": 0.821, + "args": { + "External id": 1433396,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851831954.511, "dur": 0.892, + "args": { + "External id": 1433397,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851831973.267, "dur": 222.032, + "args": { + "External id": 1433398,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851832010.850, "dur": 178.582, + "args": { + "External id": 1433399,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851832028.307, "dur": 17.939, + "args": { + "External id": 1433400,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851832050.649, "dur": 106.369, + "args": { + "External id": 1433401,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851832087.903, "dur": 68.701, + "args": { + "External id": 1433402,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832092.341, "dur": 7.031, + "args": { + "External id": 1433403,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851832101.646, "dur": 54.329, + "args": { + "External id": 1433404,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 2338706, "tid": 2379422, + "ts": 6413851832341.909, "dur": 609.636, + "args": { + "External id": 1433405,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413851832361.487, "dur": 576.440, + "args": { + "External id": 1433406,"Record function id": 0, "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851832429.552, "dur": 6.013, + "args": { + "External id": 1433407,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851832451.255, "dur": 51.262, + "args": { + "External id": 1433408,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832474.012, "dur": 1.925, + "args": { + "External id": 1433409,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832478.302, "dur": 0.585, + "args": { + "External id": 1433410,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832480.708, "dur": 0.682, + "args": { + "External id": 1433411,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832483.024, "dur": 0.448, + "args": { + "External id": 1433412,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832485.178, "dur": 0.377, + "args": { + "External id": 1433413,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832487.239, "dur": 2.913, + "args": { + "External id": 1433414,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832491.909, "dur": 0.446, + "args": { + "External id": 1433415,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832493.997, "dur": 0.407, + "args": { + "External id": 1433416,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832495.972, "dur": 0.392, + "args": { + "External id": 1433417,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851832513.516, "dur": 46.325, + "args": { + "External id": 1433418,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851832596.702, "dur": 117.215, + "args": { + "External id": 1433419,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851832607.697, "dur": 3.943, + "args": { + "External id": 1433420,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851832616.956, "dur": 10.990, + "args": { + "External id": 1433421,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851832621.691, "dur": 5.799, + "args": { + "External id": 1433422,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832625.752, "dur": 0.557, + "args": { + "External id": 1433423,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851832635.152, "dur": 28.258, + "args": { + "External id": 1433424,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832637.483, "dur": 0.630, + "args": { + "External id": 1433425,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832640.145, "dur": 0.418, + "args": { + "External id": 1433426,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832642.299, "dur": 2.806, + "args": { + "External id": 1433427,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832646.651, "dur": 0.352, + "args": { + "External id": 1433428,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832648.881, "dur": 0.390, + "args": { + "External id": 1433429,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832651.074, "dur": 0.645, + "args": { + "External id": 1433430,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832653.397, "dur": 0.394, + "args": { + "External id": 1433431,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832655.504, "dur": 0.422, + "args": { + "External id": 1433432,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851832657.553, "dur": 0.433, + "args": { + "External id": 1433433,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851832675.092, "dur": 31.070, + "args": { + "External id": 1433434,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851832760.381, "dur": 111.872, + "args": { + "External id": 1433435,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851832783.375, "dur": 85.285, + "args": { + "External id": 1433436,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3419, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851832793.241, "dur": 71.219, + "args": { + "External id": 1433437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851832884.950, "dur": 2.103, + "args": { + "External id": 1433438,"Record function id": 0, "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": 3421, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851832968.048, "dur": 1800.938, + "args": { + "External id": 1433439,"Sequence number": 15348688, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3422 + } + }, + { + "ph": "f", "id": 194, "pid": 2338706, "tid": 2379422, "ts": 6413851832968.048, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833145.126, "dur": 108.662, + "args": { + "External id": 1433440,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851833295.183, "dur": 40.899, + "args": { + "External id": 1433441,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833355.517, "dur": 49.647, + "args": { + "External id": 1433442,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833417.308, "dur": 31.839, + "args": { + "External id": 1433443,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833456.932, "dur": 32.614, + "args": { + "External id": 1433444,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833497.398, "dur": 27.819, + "args": { + "External id": 1433445,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833532.970, "dur": 29.493, + "args": { + "External id": 1433446,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851833587.185, "dur": 23.069, + "args": { + "External id": 1433447,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851833628.114, "dur": 26.831, + "args": { + "External id": 1433448,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851833676.195, "dur": 19.792, + "args": { + "External id": 1433449,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851833708.464, "dur": 14.679, + "args": { + "External id": 1433450,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833731.705, "dur": 34.766, + "args": { + "External id": 1433451,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851833770.525, "dur": 32.068, + "args": { + "External id": 1433452,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851833834.542, "dur": 318.414, + "args": { + "External id": 1433453,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851833915.271, "dur": 5.897, + "args": { + "External id": 1433454,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851833923.236, "dur": 2.856, + "args": { + "External id": 1433455,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851833927.456, "dur": 1.949, + "args": { + "External id": 1433456,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851833930.730, "dur": 2.262, + "args": { + "External id": 1433457,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851834000.592, "dur": 5.870, + "args": { + "External id": 1433458,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851834003.104, "dur": 2.946, + "args": { + "External id": 1433459,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851834008.805, "dur": 36.054, + "args": { + "External id": 1433460,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851834014.550, "dur": 4.546, + "args": { + "External id": 1433461,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851834046.661, "dur": 2.162, + "args": { + "External id": 1433462,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851834047.970, "dur": 0.762, + "args": { + "External id": 1433463,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851834050.450, "dur": 51.931, + "args": { + "External id": 1433464,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851834084.395, "dur": 1.362, + "args": { + "External id": 1433465,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851834193.225, "dur": 31.954, + "args": { + "External id": 1433466,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851834243.037, "dur": 16.507, + "args": { + "External id": 1433467,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851834268.554, "dur": 50.076, + "args": { + "External id": 1433468,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851834325.820, "dur": 38.972, + "args": { + "External id": 1433469,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851834376.911, "dur": 36.372, + "args": { + "External id": 1433470,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851834427.221, "dur": 39.463, + "args": { + "External id": 1433471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851834475.973, "dur": 29.199, + "args": { + "External id": 1433472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851834513.202, "dur": 33.447, + "args": { + "External id": 1433473,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851834566.765, "dur": 30.663, + "args": { + "External id": 1433474,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851834613.443, "dur": 26.553, + "args": { + "External id": 1433475,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851834655.575, "dur": 17.354, + "args": { + "External id": 1433476,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851834689.175, "dur": 15.155, + "args": { + "External id": 1433477,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851834717.448, "dur": 19.465, + "args": { + "External id": 1433478,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834816.395, "dur": 16.231, + "args": { + "External id": 1433479,"Record function id": 0, "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834820.063, "dur": 11.526, + "args": { + "External id": 1433480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834824.146, "dur": 6.289, + "args": { + "External id": 1433481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834826.119, "dur": 4.186, + "args": { + "External id": 1433482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834836.509, "dur": 5.477, + "args": { + "External id": 1433483,"Record function id": 0, "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834838.379, "dur": 3.109, + "args": { + "External id": 1433484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834839.027, "dur": 1.982, + "args": { + "External id": 1433485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834839.994, "dur": 0.911, + "args": { + "External id": 1433486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834845.127, "dur": 7.149, + "args": { + "External id": 1433487,"Record function id": 0, "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834846.420, "dur": 5.466, + "args": { + "External id": 1433488,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834847.069, "dur": 4.245, + "args": { + "External id": 1433489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834847.621, "dur": 3.632, + "args": { + "External id": 1433490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834855.503, "dur": 4.308, + "args": { + "External id": 1433491,"Record function id": 0, "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834856.506, "dur": 2.900, + "args": { + "External id": 1433492,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834857.091, "dur": 1.868, + "args": { + "External id": 1433493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834857.957, "dur": 0.936, + "args": { + "External id": 1433494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834862.961, "dur": 4.414, + "args": { + "External id": 1433495,"Record function id": 0, "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834864.055, "dur": 2.900, + "args": { + "External id": 1433496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834864.880, "dur": 1.540, + "args": { + "External id": 1433497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834865.640, "dur": 0.705, + "args": { + "External id": 1433498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834870.623, "dur": 4.393, + "args": { + "External id": 1433499,"Record function id": 0, "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834871.942, "dur": 2.681, + "args": { + "External id": 1433500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834872.537, "dur": 1.652, + "args": { + "External id": 1433501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834873.365, "dur": 0.707, + "args": { + "External id": 1433502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834878.196, "dur": 3.699, + "args": { + "External id": 1433503,"Record function id": 0, "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834879.378, "dur": 2.130, + "args": { + "External id": 1433504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834880.126, "dur": 0.958, + "args": { + "External id": 1433505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834880.438, "dur": 0.557, + "args": { + "External id": 1433506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834884.978, "dur": 4.261, + "args": { + "External id": 1433507,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834886.458, "dur": 2.391, + "args": { + "External id": 1433508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834886.897, "dur": 1.361, + "args": { + "External id": 1433509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834887.162, "dur": 1.030, + "args": { + "External id": 1433510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834892.517, "dur": 3.901, + "args": { + "External id": 1433511,"Record function id": 0, "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851834893.620, "dur": 2.418, + "args": { + "External id": 1433512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834894.255, "dur": 1.380, + "args": { + "External id": 1433513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851834894.754, "dur": 0.785, + "args": { + "External id": 1433514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851834900.586, "dur": 62652.829, + "args": { + "External id": 1433515,"Record function id": 0, "Sequence number": 15348687, "Fwd thread id": 1, "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851834901.799, "dur": 62642.765, + "args": { + "External id": 1433516,"Sequence number": 15348687, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3499 + } + }, + { + "ph": "f", "id": 195, "pid": 2338706, "tid": 2379422, "ts": 6413851834901.799, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413851834931.462, "dur": 40.292, + "args": { + "External id": 1433517,"Record function id": 0, "Ev Idx": 3500 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413851835003.715, "dur": 109.603, + "args": { + "External id": 1433518,"Record function id": 0, "Ev Idx": 3501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413851835121.359, "dur": 62414.826, + "args": { + "External id": 1433519,"Record function id": 0, "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851835216.413, "dur": 8.044, + "args": { + "External id": 1433520,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851835235.322, "dur": 6.903, + "args": { + "External id": 1433521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851835257.943, "dur": 61368.995, + "args": { + "External id": 1433522,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851835272.455, "dur": 61341.553, + "args": { + "External id": 1433523,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851835399.525, "dur": 18.877, + "args": { + "External id": 1433524,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851835438.491, "dur": 61126.862, + "args": { + "External id": 1433525,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851835441.857, "dur": 61122.264, + "args": { + "External id": 1433526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851835446.656, "dur": 9.562, + "args": { + "External id": 1433527,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851835458.655, "dur": 61100.242, + "args": { + "External id": 1433528,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851896741.180, "dur": 12.176, + "args": { + "External id": 1433529,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851896745.125, "dur": 7.953, + "args": { + "External id": 1433530,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851896789.550, "dur": 431.423, + "args": { + "External id": 1433531,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851896818.096, "dur": 397.151, + "args": { + "External id": 1433532,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3515, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851896829.856, "dur": 379.038, + "args": { + "External id": 1433533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851897243.403, "dur": 2.397, + "args": { + "External id": 1433534,"Record function id": 0, "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": 3517, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897310.274, "dur": 7.386, + "args": { + "External id": 1433535,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897366.948, "dur": 1.615, + "args": { + "External id": 1433536,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897385.416, "dur": 3.448, + "args": { + "External id": 1433537,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897402.242, "dur": 1.197, + "args": { + "External id": 1433538,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897415.580, "dur": 0.875, + "args": { + "External id": 1433539,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897428.911, "dur": 1.077, + "args": { + "External id": 1433540,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897442.752, "dur": 2.906, + "args": { + "External id": 1433541,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897458.490, "dur": 3.657, + "args": { + "External id": 1433542,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897473.083, "dur": 1.604, + "args": { + "External id": 1433543,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851897568.475, "dur": 3157.103, + "args": { + "External id": 1433544,"Record function id": 0, "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413851897589.033, "dur": 1165.616, + "args": { + "External id": 1433545,"Record function id": 0, "Ev Idx": 3528 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413851897605.379, "dur": 335.780, + "args": { + "External id": 1433546,"Record function id": 0, "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897694.780, "dur": 4.458, + "args": { + "External id": 1433547,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897702.981, "dur": 1.337, + "args": { + "External id": 1433548,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897706.204, "dur": 3.195, + "args": { + "External id": 1433549,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897710.908, "dur": 0.983, + "args": { + "External id": 1433550,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897713.256, "dur": 1.212, + "args": { + "External id": 1433551,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897716.039, "dur": 1.199, + "args": { + "External id": 1433552,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897718.731, "dur": 2.529, + "args": { + "External id": 1433553,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897722.551, "dur": 1.181, + "args": { + "External id": 1433554,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897725.312, "dur": 1.021, + "args": { + "External id": 1433555,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851897728.088, "dur": 0.874, + "args": { + "External id": 1433556,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851897746.580, "dur": 162.366, + "args": { + "External id": 1433557,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851897763.465, "dur": 140.754, + "args": { + "External id": 1433558,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851897787.281, "dur": 17.678, + "args": { + "External id": 1433559,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851897809.032, "dur": 66.069, + "args": { + "External id": 1433560,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851897812.104, "dur": 62.655, + "args": { + "External id": 1433561,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851897816.305, "dur": 5.442, + "args": { + "External id": 1433562,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851897823.836, "dur": 50.297, + "args": { + "External id": 1433563,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 2338706, "tid": 2379422, + "ts": 6413851898098.511, "dur": 646.630, + "args": { + "External id": 1433564,"Record function id": 0, "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413851898120.458, "dur": 611.383, + "args": { + "External id": 1433565,"Record function id": 0, "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851898191.280, "dur": 7.014, + "args": { + "External id": 1433566,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851898214.952, "dur": 58.017, + "args": { + "External id": 1433567,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898220.375, "dur": 2.126, + "args": { + "External id": 1433568,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898224.992, "dur": 0.522, + "args": { + "External id": 1433569,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898227.256, "dur": 0.564, + "args": { + "External id": 1433570,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898229.460, "dur": 0.376, + "args": { + "External id": 1433571,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898231.822, "dur": 0.501, + "args": { + "External id": 1433572,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898234.120, "dur": 2.473, + "args": { + "External id": 1433573,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898238.156, "dur": 0.935, + "args": { + "External id": 1433574,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898263.200, "dur": 0.548, + "args": { + "External id": 1433575,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898265.989, "dur": 0.395, + "args": { + "External id": 1433576,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851898290.818, "dur": 53.245, + "args": { + "External id": 1433577,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851898378.739, "dur": 121.025, + "args": { + "External id": 1433578,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851898393.039, "dur": 4.266, + "args": { + "External id": 1433579,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851898402.906, "dur": 11.052, + "args": { + "External id": 1433580,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851898407.436, "dur": 6.106, + "args": { + "External id": 1433581,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898411.687, "dur": 0.614, + "args": { + "External id": 1433582,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851898421.526, "dur": 27.786, + "args": { + "External id": 1433583,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898423.887, "dur": 0.513, + "args": { + "External id": 1433584,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898426.069, "dur": 0.431, + "args": { + "External id": 1433585,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898428.352, "dur": 2.452, + "args": { + "External id": 1433586,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898432.590, "dur": 0.530, + "args": { + "External id": 1433587,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898434.998, "dur": 0.464, + "args": { + "External id": 1433588,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898437.030, "dur": 0.597, + "args": { + "External id": 1433589,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898439.383, "dur": 0.793, + "args": { + "External id": 1433590,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898442.058, "dur": 0.455, + "args": { + "External id": 1433591,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851898444.063, "dur": 0.453, + "args": { + "External id": 1433592,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851898459.364, "dur": 32.176, + "args": { + "External id": 1433593,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851898548.879, "dur": 114.272, + "args": { + "External id": 1433594,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851898573.802, "dur": 85.603, + "args": { + "External id": 1433595,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3578, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851898583.869, "dur": 71.127, + "args": { + "External id": 1433596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851898677.617, "dur": 1.964, + "args": { + "External id": 1433597,"Record function id": 0, "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": 3580, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851898762.795, "dur": 1936.656, + "args": { + "External id": 1433598,"Sequence number": 15348686, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3581 + } + }, + { + "ph": "f", "id": 196, "pid": 2338706, "tid": 2379422, "ts": 6413851898762.795, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851898875.369, "dur": 127.067, + "args": { + "External id": 1433599,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851899045.668, "dur": 79.230, + "args": { + "External id": 1433600,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899252.674, "dur": 70.537, + "args": { + "External id": 1433601,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899338.803, "dur": 35.392, + "args": { + "External id": 1433602,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899382.054, "dur": 35.746, + "args": { + "External id": 1433603,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899425.646, "dur": 28.827, + "args": { + "External id": 1433604,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899462.140, "dur": 29.665, + "args": { + "External id": 1433605,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851899520.817, "dur": 25.287, + "args": { + "External id": 1433606,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851899565.052, "dur": 30.098, + "args": { + "External id": 1433607,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851899614.588, "dur": 19.223, + "args": { + "External id": 1433608,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851899645.766, "dur": 14.038, + "args": { + "External id": 1433609,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899668.668, "dur": 36.912, + "args": { + "External id": 1433610,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851899709.536, "dur": 32.735, + "args": { + "External id": 1433611,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851899775.390, "dur": 274.089, + "args": { + "External id": 1433612,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851899857.868, "dur": 5.925, + "args": { + "External id": 1433613,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851899865.966, "dur": 2.576, + "args": { + "External id": 1433614,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851899869.886, "dur": 1.631, + "args": { + "External id": 1433615,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851899872.642, "dur": 1.723, + "args": { + "External id": 1433616,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851899919.880, "dur": 5.344, + "args": { + "External id": 1433617,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851899922.160, "dur": 2.896, + "args": { + "External id": 1433618,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851899927.501, "dur": 34.394, + "args": { + "External id": 1433619,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851899932.583, "dur": 4.035, + "args": { + "External id": 1433620,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851899963.643, "dur": 1.843, + "args": { + "External id": 1433621,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851899964.681, "dur": 0.730, + "args": { + "External id": 1433622,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851899966.970, "dur": 34.755, + "args": { + "External id": 1433623,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851899968.908, "dur": 0.703, + "args": { + "External id": 1433624,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851900126.408, "dur": 31.185, + "args": { + "External id": 1433625,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851900174.475, "dur": 17.860, + "args": { + "External id": 1433626,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851900202.084, "dur": 48.173, + "args": { + "External id": 1433627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851900258.000, "dur": 39.611, + "args": { + "External id": 1433628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851900309.521, "dur": 37.160, + "args": { + "External id": 1433629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851900360.694, "dur": 36.644, + "args": { + "External id": 1433630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851900406.742, "dur": 27.737, + "args": { + "External id": 1433631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851900442.154, "dur": 31.223, + "args": { + "External id": 1433632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851900493.121, "dur": 28.575, + "args": { + "External id": 1433633,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851900537.431, "dur": 27.676, + "args": { + "External id": 1433634,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851900584.071, "dur": 16.878, + "args": { + "External id": 1433635,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851900617.958, "dur": 20.200, + "args": { + "External id": 1433636,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851900650.817, "dur": 17.908, + "args": { + "External id": 1433637,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900748.543, "dur": 16.673, + "args": { + "External id": 1433638,"Record function id": 0, "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900752.051, "dur": 12.101, + "args": { + "External id": 1433639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900756.428, "dur": 6.483, + "args": { + "External id": 1433640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900758.678, "dur": 4.100, + "args": { + "External id": 1433641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900769.367, "dur": 4.854, + "args": { + "External id": 1433642,"Record function id": 0, "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900770.549, "dur": 3.209, + "args": { + "External id": 1433643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900771.343, "dur": 1.803, + "args": { + "External id": 1433644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900771.958, "dur": 1.069, + "args": { + "External id": 1433645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900777.672, "dur": 6.533, + "args": { + "External id": 1433646,"Record function id": 0, "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900779.126, "dur": 4.666, + "args": { + "External id": 1433647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900779.623, "dur": 3.597, + "args": { + "External id": 1433648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900779.992, "dur": 3.169, + "args": { + "External id": 1433649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900787.492, "dur": 3.828, + "args": { + "External id": 1433650,"Record function id": 0, "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900788.623, "dur": 2.277, + "args": { + "External id": 1433651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900789.323, "dur": 1.116, + "args": { + "External id": 1433652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900789.609, "dur": 0.771, + "args": { + "External id": 1433653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900794.459, "dur": 4.326, + "args": { + "External id": 1433654,"Record function id": 0, "Ev Idx": 3637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900796.086, "dur": 2.289, + "args": { + "External id": 1433655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900796.573, "dur": 1.385, + "args": { + "External id": 1433656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900797.330, "dur": 0.559, + "args": { + "External id": 1433657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900801.954, "dur": 4.276, + "args": { + "External id": 1433658,"Record function id": 0, "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900803.176, "dur": 2.641, + "args": { + "External id": 1433659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900803.849, "dur": 1.437, + "args": { + "External id": 1433660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900804.565, "dur": 0.604, + "args": { + "External id": 1433661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900809.519, "dur": 3.923, + "args": { + "External id": 1433662,"Record function id": 0, "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900810.896, "dur": 2.134, + "args": { + "External id": 1433663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900811.419, "dur": 1.183, + "args": { + "External id": 1433664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900811.911, "dur": 0.610, + "args": { + "External id": 1433665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900816.527, "dur": 3.452, + "args": { + "External id": 1433666,"Record function id": 0, "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900817.471, "dur": 2.091, + "args": { + "External id": 1433667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900818.093, "dur": 1.048, + "args": { + "External id": 1433668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900818.386, "dur": 0.686, + "args": { + "External id": 1433669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900823.124, "dur": 3.855, + "args": { + "External id": 1433670,"Record function id": 0, "Ev Idx": 3653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851900824.214, "dur": 2.359, + "args": { + "External id": 1433671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900824.770, "dur": 1.341, + "args": { + "External id": 1433672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851900825.390, "dur": 0.635, + "args": { + "External id": 1433673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851900831.344, "dur": 64192.887, + "args": { + "External id": 1433674,"Record function id": 0, "Sequence number": 15348685, "Fwd thread id": 1, "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851900832.761, "dur": 64180.650, + "args": { + "External id": 1433675,"Sequence number": 15348685, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3658 + } + }, + { + "ph": "f", "id": 197, "pid": 2338706, "tid": 2379422, "ts": 6413851900832.761, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413851900863.419, "dur": 38.575, + "args": { + "External id": 1433676,"Record function id": 0, "Ev Idx": 3659 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413851900909.545, "dur": 83.894, + "args": { + "External id": 1433677,"Record function id": 0, "Ev Idx": 3660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413851901002.983, "dur": 64001.801, + "args": { + "External id": 1433678,"Record function id": 0, "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851901136.832, "dur": 8.396, + "args": { + "External id": 1433679,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851901156.496, "dur": 6.855, + "args": { + "External id": 1433680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851901180.972, "dur": 62979.597, + "args": { + "External id": 1433681,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851901195.569, "dur": 62951.997, + "args": { + "External id": 1433682,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851901305.006, "dur": 18.025, + "args": { + "External id": 1433683,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851901343.266, "dur": 62754.390, + "args": { + "External id": 1433684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851901346.690, "dur": 62750.017, + "args": { + "External id": 1433685,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851901351.032, "dur": 10.320, + "args": { + "External id": 1433686,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851901363.763, "dur": 62727.966, + "args": { + "External id": 1433687,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851964269.997, "dur": 13.025, + "args": { + "External id": 1433688,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851964274.288, "dur": 8.347, + "args": { + "External id": 1433689,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851964314.934, "dur": 372.876, + "args": { + "External id": 1433690,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851964343.105, "dur": 339.289, + "args": { + "External id": 1433691,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3674, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851964355.179, "dur": 321.498, + "args": { + "External id": 1433692,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851964706.628, "dur": 2.476, + "args": { + "External id": 1433693,"Record function id": 0, "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": 3676, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964767.834, "dur": 6.537, + "args": { + "External id": 1433694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964820.775, "dur": 1.528, + "args": { + "External id": 1433695,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964841.369, "dur": 2.928, + "args": { + "External id": 1433696,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964857.548, "dur": 1.121, + "args": { + "External id": 1433697,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964869.896, "dur": 0.884, + "args": { + "External id": 1433698,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964882.011, "dur": 1.024, + "args": { + "External id": 1433699,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964894.376, "dur": 3.017, + "args": { + "External id": 1433700,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964908.447, "dur": 2.779, + "args": { + "External id": 1433701,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851964922.537, "dur": 1.013, + "args": { + "External id": 1433702,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851965041.196, "dur": 3092.587, + "args": { + "External id": 1433703,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413851965095.818, "dur": 1182.385, + "args": { + "External id": 1433704,"Record function id": 0, "Ev Idx": 3687 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413851965112.363, "dur": 389.431, + "args": { + "External id": 1433705,"Record function id": 0, "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965214.766, "dur": 5.075, + "args": { + "External id": 1433706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965223.286, "dur": 1.592, + "args": { + "External id": 1433707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965226.681, "dur": 3.052, + "args": { + "External id": 1433708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965231.226, "dur": 1.144, + "args": { + "External id": 1433709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965233.980, "dur": 1.154, + "args": { + "External id": 1433710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965236.798, "dur": 0.859, + "args": { + "External id": 1433711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965239.333, "dur": 2.479, + "args": { + "External id": 1433712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965243.313, "dur": 0.947, + "args": { + "External id": 1433713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965245.599, "dur": 0.989, + "args": { + "External id": 1433714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851965248.001, "dur": 1.028, + "args": { + "External id": 1433715,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851965266.930, "dur": 200.331, + "args": { + "External id": 1433716,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851965325.597, "dur": 136.250, + "args": { + "External id": 1433717,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851965343.409, "dur": 17.667, + "args": { + "External id": 1433718,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851965365.127, "dur": 65.762, + "args": { + "External id": 1433719,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851965368.160, "dur": 62.409, + "args": { + "External id": 1433720,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965372.128, "dur": 5.287, + "args": { + "External id": 1433721,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851965379.262, "dur": 50.579, + "args": { + "External id": 1433722,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 2338706, "tid": 2379422, + "ts": 6413851965598.842, "dur": 670.988, + "args": { + "External id": 1433723,"Record function id": 0, "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413851965615.949, "dur": 640.496, + "args": { + "External id": 1433724,"Record function id": 0, "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851965679.225, "dur": 5.109, + "args": { + "External id": 1433725,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851965700.177, "dur": 32.440, + "args": { + "External id": 1433726,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965705.314, "dur": 1.940, + "args": { + "External id": 1433727,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965709.759, "dur": 0.524, + "args": { + "External id": 1433728,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965711.959, "dur": 0.471, + "args": { + "External id": 1433729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965714.033, "dur": 0.617, + "args": { + "External id": 1433730,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965716.548, "dur": 0.615, + "args": { + "External id": 1433731,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965718.922, "dur": 2.343, + "args": { + "External id": 1433732,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965722.534, "dur": 0.710, + "args": { + "External id": 1433733,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965724.751, "dur": 0.566, + "args": { + "External id": 1433734,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965726.780, "dur": 0.374, + "args": { + "External id": 1433735,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851965744.384, "dur": 43.176, + "args": { + "External id": 1433736,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413851965839.764, "dur": 119.308, + "args": { + "External id": 1433737,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851965850.798, "dur": 4.099, + "args": { + "External id": 1433738,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413851965860.816, "dur": 11.362, + "args": { + "External id": 1433739,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413851965865.314, "dur": 6.318, + "args": { + "External id": 1433740,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965869.742, "dur": 0.656, + "args": { + "External id": 1433741,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413851965878.953, "dur": 27.708, + "args": { + "External id": 1433742,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965881.813, "dur": 0.483, + "args": { + "External id": 1433743,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965884.014, "dur": 0.402, + "args": { + "External id": 1433744,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965885.904, "dur": 2.376, + "args": { + "External id": 1433745,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965889.652, "dur": 0.466, + "args": { + "External id": 1433746,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965891.881, "dur": 0.657, + "args": { + "External id": 1433747,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965894.139, "dur": 0.660, + "args": { + "External id": 1433748,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965896.513, "dur": 0.370, + "args": { + "External id": 1433749,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965898.632, "dur": 0.481, + "args": { + "External id": 1433750,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851965900.857, "dur": 0.444, + "args": { + "External id": 1433751,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851965918.432, "dur": 32.924, + "args": { + "External id": 1433752,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413851966028.572, "dur": 151.542, + "args": { + "External id": 1433753,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851966052.340, "dur": 123.643, + "args": { + "External id": 1433754,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3737, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413851966094.618, "dur": 77.099, + "args": { + "External id": 1433755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413851966195.723, "dur": 1.913, + "args": { + "External id": 1433756,"Record function id": 0, "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": 3739, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851966285.559, "dur": 1823.421, + "args": { + "External id": 1433757,"Sequence number": 15348684, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3740 + } + }, + { + "ph": "f", "id": 198, "pid": 2338706, "tid": 2379422, "ts": 6413851966285.559, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851966400.779, "dur": 112.220, + "args": { + "External id": 1433758,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851966551.612, "dur": 40.294, + "args": { + "External id": 1433759,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413851966610.194, "dur": 47.536, + "args": { + "External id": 1433760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851966670.753, "dur": 32.399, + "args": { + "External id": 1433761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851966710.907, "dur": 32.556, + "args": { + "External id": 1433762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851966750.431, "dur": 28.033, + "args": { + "External id": 1433763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851966787.042, "dur": 28.924, + "args": { + "External id": 1433764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851966840.078, "dur": 23.755, + "args": { + "External id": 1433765,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413851966885.137, "dur": 29.593, + "args": { + "External id": 1433766,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851966934.140, "dur": 18.331, + "args": { + "External id": 1433767,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851966964.099, "dur": 36.728, + "args": { + "External id": 1433768,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967012.632, "dur": 76.805, + "args": { + "External id": 1433769,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967095.416, "dur": 37.976, + "args": { + "External id": 1433770,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413851967179.793, "dur": 256.295, + "args": { + "External id": 1433771,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851967262.694, "dur": 6.824, + "args": { + "External id": 1433772,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851967271.844, "dur": 2.227, + "args": { + "External id": 1433773,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851967275.281, "dur": 2.566, + "args": { + "External id": 1433774,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851967279.418, "dur": 1.766, + "args": { + "External id": 1433775,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851967328.749, "dur": 5.411, + "args": { + "External id": 1433776,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851967330.902, "dur": 3.075, + "args": { + "External id": 1433777,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851967336.471, "dur": 34.417, + "args": { + "External id": 1433778,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851967341.844, "dur": 4.494, + "args": { + "External id": 1433779,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413851967372.513, "dur": 1.941, + "args": { + "External id": 1433780,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851967373.589, "dur": 0.778, + "args": { + "External id": 1433781,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413851967375.750, "dur": 14.738, + "args": { + "External id": 1433782,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851967377.336, "dur": 0.639, + "args": { + "External id": 1433783,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413851967474.352, "dur": 26.701, + "args": { + "External id": 1433784,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851967516.812, "dur": 17.035, + "args": { + "External id": 1433785,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967542.393, "dur": 42.560, + "args": { + "External id": 1433786,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967592.205, "dur": 40.289, + "args": { + "External id": 1433787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967642.714, "dur": 21.786, + "args": { + "External id": 1433788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967670.994, "dur": 31.994, + "args": { + "External id": 1433789,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967710.676, "dur": 47.752, + "args": { + "External id": 1433790,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413851967774.122, "dur": 36.121, + "args": { + "External id": 1433791,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413851967829.847, "dur": 24.410, + "args": { + "External id": 1433792,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851967869.001, "dur": 26.022, + "args": { + "External id": 1433793,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413851967909.703, "dur": 23.012, + "args": { + "External id": 1433794,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413851967948.725, "dur": 16.189, + "args": { + "External id": 1433795,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413851968004.523, "dur": 21.228, + "args": { + "External id": 1433796,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968161.072, "dur": 16.302, + "args": { + "External id": 1433797,"Record function id": 0, "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968164.561, "dur": 11.786, + "args": { + "External id": 1433798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968169.217, "dur": 6.176, + "args": { + "External id": 1433799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968171.012, "dur": 4.258, + "args": { + "External id": 1433800,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968181.353, "dur": 5.492, + "args": { + "External id": 1433801,"Record function id": 0, "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968182.755, "dur": 3.626, + "args": { + "External id": 1433802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968183.603, "dur": 2.268, + "args": { + "External id": 1433803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968184.536, "dur": 1.176, + "args": { + "External id": 1433804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968190.083, "dur": 7.336, + "args": { + "External id": 1433805,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968191.739, "dur": 5.243, + "args": { + "External id": 1433806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968192.392, "dur": 4.174, + "args": { + "External id": 1433807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968192.718, "dur": 3.761, + "args": { + "External id": 1433808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968200.572, "dur": 3.859, + "args": { + "External id": 1433809,"Record function id": 0, "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968201.581, "dur": 2.436, + "args": { + "External id": 1433810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968202.098, "dur": 1.256, + "args": { + "External id": 1433811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968202.452, "dur": 0.816, + "args": { + "External id": 1433812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968207.561, "dur": 4.096, + "args": { + "External id": 1433813,"Record function id": 0, "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968208.760, "dur": 2.478, + "args": { + "External id": 1433814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968209.546, "dur": 1.293, + "args": { + "External id": 1433815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968210.012, "dur": 0.759, + "args": { + "External id": 1433816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968214.750, "dur": 4.470, + "args": { + "External id": 1433817,"Record function id": 0, "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968216.001, "dur": 2.780, + "args": { + "External id": 1433818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968216.854, "dur": 1.476, + "args": { + "External id": 1433819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968217.391, "dur": 0.819, + "args": { + "External id": 1433820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968222.625, "dur": 3.654, + "args": { + "External id": 1433821,"Record function id": 0, "Ev Idx": 3804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968223.906, "dur": 1.958, + "args": { + "External id": 1433822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968224.386, "dur": 1.081, + "args": { + "External id": 1433823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968224.794, "dur": 0.558, + "args": { + "External id": 1433824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968229.466, "dur": 3.746, + "args": { + "External id": 1433825,"Record function id": 0, "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968230.706, "dur": 2.094, + "args": { + "External id": 1433826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968231.157, "dur": 1.002, + "args": { + "External id": 1433827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968231.474, "dur": 0.618, + "args": { + "External id": 1433828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968236.419, "dur": 3.702, + "args": { + "External id": 1433829,"Record function id": 0, "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413851968237.583, "dur": 2.112, + "args": { + "External id": 1433830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968238.015, "dur": 1.277, + "args": { + "External id": 1433831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413851968238.506, "dur": 0.700, + "args": { + "External id": 1433832,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851968244.362, "dur": 63055.421, + "args": { + "External id": 1433833,"Record function id": 0, "Sequence number": 15348683, "Fwd thread id": 1, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413851968245.563, "dur": 63044.419, + "args": { + "External id": 1433834,"Sequence number": 15348683, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3817 + } + }, + { + "ph": "f", "id": 199, "pid": 2338706, "tid": 2379422, "ts": 6413851968245.563, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413851968277.591, "dur": 41.923, + "args": { + "External id": 1433835,"Record function id": 0, "Ev Idx": 3818 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413851968327.527, "dur": 69.247, + "args": { + "External id": 1433836,"Record function id": 0, "Ev Idx": 3819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413851968403.156, "dur": 62877.425, + "args": { + "External id": 1433837,"Record function id": 0, "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851968494.368, "dur": 7.198, + "args": { + "External id": 1433838,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413851968511.064, "dur": 7.349, + "args": { + "External id": 1433839,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851968533.762, "dur": 61796.796, + "args": { + "External id": 1433840,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413851968548.480, "dur": 61768.822, + "args": { + "External id": 1433841,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413851968649.713, "dur": 18.221, + "args": { + "External id": 1433842,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413851968687.796, "dur": 61581.296, + "args": { + "External id": 1433843,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413851968691.123, "dur": 61576.742, + "args": { + "External id": 1433844,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413851968695.923, "dur": 9.954, + "args": { + "External id": 1433845,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413851968707.828, "dur": 61554.743, + "args": { + "External id": 1433846,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852030441.520, "dur": 13.702, + "args": { + "External id": 1433847,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852030445.447, "dur": 9.369, + "args": { + "External id": 1433848,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852030487.765, "dur": 424.693, + "args": { + "External id": 1433849,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852030516.120, "dur": 390.840, + "args": { + "External id": 1433850,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3833, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852030528.062, "dur": 373.433, + "args": { + "External id": 1433851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852030930.844, "dur": 2.513, + "args": { + "External id": 1433852,"Record function id": 0, "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": 3835, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031015.822, "dur": 7.333, + "args": { + "External id": 1433853,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031106.663, "dur": 2.449, + "args": { + "External id": 1433854,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031127.832, "dur": 3.074, + "args": { + "External id": 1433855,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031143.241, "dur": 0.814, + "args": { + "External id": 1433856,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031156.282, "dur": 1.000, + "args": { + "External id": 1433857,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031168.601, "dur": 0.965, + "args": { + "External id": 1433858,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031181.645, "dur": 3.368, + "args": { + "External id": 1433859,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031197.366, "dur": 3.295, + "args": { + "External id": 1433860,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031212.106, "dur": 1.014, + "args": { + "External id": 1433861,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852031317.835, "dur": 3028.479, + "args": { + "External id": 1433862,"Record function id": 0, "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413852031339.685, "dur": 1141.746, + "args": { + "External id": 1433863,"Record function id": 0, "Ev Idx": 3846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413852031356.160, "dur": 347.231, + "args": { + "External id": 1433864,"Record function id": 0, "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031452.523, "dur": 4.439, + "args": { + "External id": 1433865,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031460.354, "dur": 1.115, + "args": { + "External id": 1433866,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031463.350, "dur": 3.404, + "args": { + "External id": 1433867,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031468.329, "dur": 0.851, + "args": { + "External id": 1433868,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031471.102, "dur": 1.361, + "args": { + "External id": 1433869,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031474.212, "dur": 1.175, + "args": { + "External id": 1433870,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 3853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031477.077, "dur": 2.330, + "args": { + "External id": 1433871,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 3854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031480.822, "dur": 0.869, + "args": { + "External id": 1433872,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031483.606, "dur": 0.860, + "args": { + "External id": 1433873,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852031485.737, "dur": 1.073, + "args": { + "External id": 1433874,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 3857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852031505.369, "dur": 165.061, + "args": { + "External id": 1433875,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852031521.266, "dur": 144.182, + "args": { + "External id": 1433876,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 3859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852031545.951, "dur": 18.619, + "args": { + "External id": 1433877,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852031568.328, "dur": 67.137, + "args": { + "External id": 1433878,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 3861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852031571.346, "dur": 63.771, + "args": { + "External id": 1433879,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 3862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031575.441, "dur": 5.686, + "args": { + "External id": 1433880,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852031583.326, "dur": 51.298, + "args": { + "External id": 1433881,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 3864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 2338706, "tid": 2379422, + "ts": 6413852031796.740, "dur": 675.966, + "args": { + "External id": 1433882,"Record function id": 0, "Ev Idx": 3865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413852031814.882, "dur": 644.699, + "args": { + "External id": 1433883,"Record function id": 0, "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852031879.144, "dur": 5.361, + "args": { + "External id": 1433884,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852031900.408, "dur": 31.437, + "args": { + "External id": 1433885,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031905.542, "dur": 1.320, + "args": { + "External id": 1433886,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031909.422, "dur": 0.574, + "args": { + "External id": 1433887,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031911.638, "dur": 0.652, + "args": { + "External id": 1433888,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031914.229, "dur": 0.517, + "args": { + "External id": 1433889,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031916.692, "dur": 0.489, + "args": { + "External id": 1433890,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031918.642, "dur": 2.513, + "args": { + "External id": 1433891,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031922.678, "dur": 0.375, + "args": { + "External id": 1433892,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031924.385, "dur": 0.371, + "args": { + "External id": 1433893,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852031926.253, "dur": 0.377, + "args": { + "External id": 1433894,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852031942.551, "dur": 67.548, + "args": { + "External id": 1433895,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852032045.538, "dur": 177.752, + "args": { + "External id": 1433896,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 3879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852032090.680, "dur": 5.432, + "args": { + "External id": 1433897,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852032102.484, "dur": 12.122, + "args": { + "External id": 1433898,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852032107.684, "dur": 6.496, + "args": { + "External id": 1433899,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 3882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032111.780, "dur": 0.804, + "args": { + "External id": 1433900,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 3883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852032122.515, "dur": 46.033, + "args": { + "External id": 1433901,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 3884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032125.088, "dur": 0.443, + "args": { + "External id": 1433902,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032127.828, "dur": 0.662, + "args": { + "External id": 1433903,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032148.108, "dur": 2.974, + "args": { + "External id": 1433904,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032152.784, "dur": 0.467, + "args": { + "External id": 1433905,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032154.802, "dur": 0.442, + "args": { + "External id": 1433906,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032157.035, "dur": 0.367, + "args": { + "External id": 1433907,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032158.895, "dur": 0.576, + "args": { + "External id": 1433908,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032161.173, "dur": 0.420, + "args": { + "External id": 1433909,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852032162.981, "dur": 0.374, + "args": { + "External id": 1433910,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852032180.009, "dur": 34.811, + "args": { + "External id": 1433911,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 3894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852032277.862, "dur": 113.848, + "args": { + "External id": 1433912,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 3895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852032300.799, "dur": 87.115, + "args": { + "External id": 1433913,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3896, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852032311.007, "dur": 72.856, + "args": { + "External id": 1433914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 3897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852032406.118, "dur": 1.700, + "args": { + "External id": 1433915,"Record function id": 0, "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": 3898, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852032488.357, "dur": 1834.370, + "args": { + "External id": 1433916,"Sequence number": 15348682, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3899 + } + }, + { + "ph": "f", "id": 200, "pid": 2338706, "tid": 2379422, "ts": 6413852032488.357, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852032605.575, "dur": 103.627, + "args": { + "External id": 1433917,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 3900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852032748.699, "dur": 43.702, + "args": { + "External id": 1433918,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 3901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852032811.890, "dur": 48.938, + "args": { + "External id": 1433919,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852032873.218, "dur": 32.650, + "args": { + "External id": 1433920,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852032913.066, "dur": 34.200, + "args": { + "External id": 1433921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852032954.629, "dur": 51.669, + "args": { + "External id": 1433922,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 3905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033017.583, "dur": 34.567, + "args": { + "External id": 1433923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852033118.499, "dur": 28.893, + "args": { + "External id": 1433924,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 3907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852033166.922, "dur": 31.757, + "args": { + "External id": 1433925,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852033221.037, "dur": 21.078, + "args": { + "External id": 1433926,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852033255.089, "dur": 15.540, + "args": { + "External id": 1433927,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033280.541, "dur": 41.251, + "args": { + "External id": 1433928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033325.716, "dur": 34.233, + "args": { + "External id": 1433929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852033394.601, "dur": 263.685, + "args": { + "External id": 1433930,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852033480.478, "dur": 5.889, + "args": { + "External id": 1433931,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852033488.646, "dur": 2.468, + "args": { + "External id": 1433932,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852033492.267, "dur": 1.688, + "args": { + "External id": 1433933,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852033495.435, "dur": 1.872, + "args": { + "External id": 1433934,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852033548.318, "dur": 4.937, + "args": { + "External id": 1433935,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852033550.467, "dur": 2.642, + "args": { + "External id": 1433936,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852033555.653, "dur": 36.504, + "args": { + "External id": 1433937,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852033561.260, "dur": 3.617, + "args": { + "External id": 1433938,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852033594.027, "dur": 1.850, + "args": { + "External id": 1433939,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852033595.053, "dur": 0.740, + "args": { + "External id": 1433940,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 3923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852033597.060, "dur": 15.529, + "args": { + "External id": 1433941,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 3924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852033598.870, "dur": 0.940, + "args": { + "External id": 1433942,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 3925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852033695.557, "dur": 27.459, + "args": { + "External id": 1433943,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852033740.156, "dur": 18.057, + "args": { + "External id": 1433944,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033767.081, "dur": 40.798, + "args": { + "External id": 1433945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033815.088, "dur": 38.295, + "args": { + "External id": 1433946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033864.246, "dur": 22.348, + "args": { + "External id": 1433947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033908.011, "dur": 43.373, + "args": { + "External id": 1433948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 3931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852033961.101, "dur": 52.428, + "args": { + "External id": 1433949,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 3932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852034024.256, "dur": 71.917, + "args": { + "External id": 1433950,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 3933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852034121.359, "dur": 32.757, + "args": { + "External id": 1433951,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852034170.440, "dur": 25.573, + "args": { + "External id": 1433952,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852034211.169, "dur": 17.912, + "args": { + "External id": 1433953,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852034245.696, "dur": 14.831, + "args": { + "External id": 1433954,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852034273.467, "dur": 16.052, + "args": { + "External id": 1433955,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034369.610, "dur": 15.889, + "args": { + "External id": 1433956,"Record function id": 0, "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034373.132, "dur": 11.435, + "args": { + "External id": 1433957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034377.477, "dur": 6.242, + "args": { + "External id": 1433958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034379.341, "dur": 4.227, + "args": { + "External id": 1433959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034389.515, "dur": 5.486, + "args": { + "External id": 1433960,"Record function id": 0, "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034390.897, "dur": 3.581, + "args": { + "External id": 1433961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034391.608, "dur": 2.240, + "args": { + "External id": 1433962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034392.619, "dur": 1.106, + "args": { + "External id": 1433963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034398.185, "dur": 6.654, + "args": { + "External id": 1433964,"Record function id": 0, "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034399.574, "dur": 4.830, + "args": { + "External id": 1433965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034400.127, "dur": 3.690, + "args": { + "External id": 1433966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034400.411, "dur": 3.317, + "args": { + "External id": 1433967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 3950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034408.134, "dur": 4.709, + "args": { + "External id": 1433968,"Record function id": 0, "Ev Idx": 3951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034409.419, "dur": 3.003, + "args": { + "External id": 1433969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034410.475, "dur": 1.555, + "args": { + "External id": 1433970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034410.987, "dur": 0.982, + "args": { + "External id": 1433971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 3954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034415.984, "dur": 4.606, + "args": { + "External id": 1433972,"Record function id": 0, "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034417.468, "dur": 2.674, + "args": { + "External id": 1433973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034418.202, "dur": 1.238, + "args": { + "External id": 1433974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034418.641, "dur": 0.733, + "args": { + "External id": 1433975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034423.762, "dur": 3.975, + "args": { + "External id": 1433976,"Record function id": 0, "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034425.021, "dur": 2.264, + "args": { + "External id": 1433977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034425.609, "dur": 1.092, + "args": { + "External id": 1433978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034426.005, "dur": 0.584, + "args": { + "External id": 1433979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 3962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034431.104, "dur": 27.527, + "args": { + "External id": 1433980,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034432.187, "dur": 25.972, + "args": { + "External id": 1433981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034432.729, "dur": 24.734, + "args": { + "External id": 1433982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034456.613, "dur": 0.728, + "args": { + "External id": 1433983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034461.949, "dur": 3.816, + "args": { + "External id": 1433984,"Record function id": 0, "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034463.086, "dur": 2.168, + "args": { + "External id": 1433985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034463.595, "dur": 1.057, + "args": { + "External id": 1433986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034464.058, "dur": 0.528, + "args": { + "External id": 1433987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 3970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034468.876, "dur": 6.255, + "args": { + "External id": 1433988,"Record function id": 0, "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852034470.169, "dur": 4.547, + "args": { + "External id": 1433989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034470.631, "dur": 3.495, + "args": { + "External id": 1433990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852034473.328, "dur": 0.699, + "args": { + "External id": 1433991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 3974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852034479.270, "dur": 63823.544, + "args": { + "External id": 1433992,"Record function id": 0, "Sequence number": 15348681, "Fwd thread id": 1, "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852034480.642, "dur": 63811.415, + "args": { + "External id": 1433993,"Sequence number": 15348681, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 3976 + } + }, + { + "ph": "f", "id": 201, "pid": 2338706, "tid": 2379422, "ts": 6413852034480.642, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413852034513.654, "dur": 41.973, + "args": { + "External id": 1433994,"Record function id": 0, "Ev Idx": 3977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413852034563.144, "dur": 65.410, + "args": { + "External id": 1433995,"Record function id": 0, "Ev Idx": 3978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413852034634.041, "dur": 63649.014, + "args": { + "External id": 1433996,"Record function id": 0, "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852034723.851, "dur": 7.211, + "args": { + "External id": 1433997,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852034740.777, "dur": 6.556, + "args": { + "External id": 1433998,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 3981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852034761.893, "dur": 62628.178, + "args": { + "External id": 1433999,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852034775.512, "dur": 62601.260, + "args": { + "External id": 1434000,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852034863.977, "dur": 17.675, + "args": { + "External id": 1434001,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852034901.789, "dur": 62424.998, + "args": { + "External id": 1434002,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 3985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852034905.280, "dur": 62420.424, + "args": { + "External id": 1434003,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 3986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852034909.852, "dur": 9.674, + "args": { + "External id": 1434004,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852034922.190, "dur": 62397.914, + "args": { + "External id": 1434005,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 3988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852097504.219, "dur": 13.908, + "args": { + "External id": 1434006,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 3989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852097508.624, "dur": 9.059, + "args": { + "External id": 1434007,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852097551.184, "dur": 373.833, + "args": { + "External id": 1434008,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 3991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852097580.158, "dur": 339.638, + "args": { + "External id": 1434009,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3992, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852097592.214, "dur": 322.304, + "args": { + "External id": 1434010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 3993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852097946.190, "dur": 2.102, + "args": { + "External id": 1434011,"Record function id": 0, "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": 3994, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098030.842, "dur": 7.231, + "args": { + "External id": 1434012,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098118.274, "dur": 2.216, + "args": { + "External id": 1434013,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098139.559, "dur": 3.868, + "args": { + "External id": 1434014,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098155.532, "dur": 0.834, + "args": { + "External id": 1434015,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098167.421, "dur": 0.927, + "args": { + "External id": 1434016,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 3999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098178.766, "dur": 1.006, + "args": { + "External id": 1434017,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098191.586, "dur": 3.240, + "args": { + "External id": 1434018,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098207.123, "dur": 2.228, + "args": { + "External id": 1434019,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098219.669, "dur": 0.941, + "args": { + "External id": 1434020,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852098319.497, "dur": 3018.453, + "args": { + "External id": 1434021,"Record function id": 0, "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413852098340.324, "dur": 1116.474, + "args": { + "External id": 1434022,"Record function id": 0, "Ev Idx": 4005 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413852098354.419, "dur": 329.075, + "args": { + "External id": 1434023,"Record function id": 0, "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098448.796, "dur": 3.863, + "args": { + "External id": 1434024,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098456.164, "dur": 0.799, + "args": { + "External id": 1434025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098458.974, "dur": 2.931, + "args": { + "External id": 1434026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098463.851, "dur": 0.988, + "args": { + "External id": 1434027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098466.271, "dur": 1.168, + "args": { + "External id": 1434028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098468.959, "dur": 1.085, + "args": { + "External id": 1434029,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098473.634, "dur": 2.221, + "args": { + "External id": 1434030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098477.436, "dur": 0.672, + "args": { + "External id": 1434031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098479.518, "dur": 0.719, + "args": { + "External id": 1434032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852098481.788, "dur": 0.651, + "args": { + "External id": 1434033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852098502.902, "dur": 151.447, + "args": { + "External id": 1434034,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852098519.782, "dur": 130.146, + "args": { + "External id": 1434035,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852098537.464, "dur": 17.107, + "args": { + "External id": 1434036,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852098558.244, "dur": 64.052, + "args": { + "External id": 1434037,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852098560.905, "dur": 61.096, + "args": { + "External id": 1434038,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098564.436, "dur": 6.151, + "args": { + "External id": 1434039,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852098572.121, "dur": 49.235, + "args": { + "External id": 1434040,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4023 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 2338706, "tid": 2379422, + "ts": 6413852098773.920, "dur": 674.892, + "args": { + "External id": 1434041,"Record function id": 0, "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413852098790.615, "dur": 645.146, + "args": { + "External id": 1434042,"Record function id": 0, "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852098850.504, "dur": 6.555, + "args": { + "External id": 1434043,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852098873.040, "dur": 29.051, + "args": { + "External id": 1434044,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098877.633, "dur": 1.420, + "args": { + "External id": 1434045,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098881.091, "dur": 1.104, + "args": { + "External id": 1434046,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098883.840, "dur": 0.383, + "args": { + "External id": 1434047,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098885.721, "dur": 0.419, + "args": { + "External id": 1434048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098887.900, "dur": 0.336, + "args": { + "External id": 1434049,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098889.646, "dur": 2.391, + "args": { + "External id": 1434050,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098894.014, "dur": 0.493, + "args": { + "External id": 1434051,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098895.846, "dur": 0.440, + "args": { + "External id": 1434052,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852098897.580, "dur": 0.285, + "args": { + "External id": 1434053,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852098913.071, "dur": 40.258, + "args": { + "External id": 1434054,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852099005.916, "dur": 180.253, + "args": { + "External id": 1434055,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852099017.657, "dur": 5.300, + "args": { + "External id": 1434056,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852099028.414, "dur": 11.522, + "args": { + "External id": 1434057,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852099032.790, "dur": 6.711, + "args": { + "External id": 1434058,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099036.944, "dur": 0.995, + "args": { + "External id": 1434059,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852099047.311, "dur": 59.922, + "args": { + "External id": 1434060,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099049.516, "dur": 0.441, + "args": { + "External id": 1434061,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099051.658, "dur": 0.254, + "args": { + "External id": 1434062,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099087.996, "dur": 2.586, + "args": { + "External id": 1434063,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099092.609, "dur": 0.442, + "args": { + "External id": 1434064,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099094.578, "dur": 0.448, + "args": { + "External id": 1434065,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099096.603, "dur": 0.408, + "args": { + "External id": 1434066,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099098.937, "dur": 0.258, + "args": { + "External id": 1434067,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099100.652, "dur": 0.514, + "args": { + "External id": 1434068,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852099102.522, "dur": 0.260, + "args": { + "External id": 1434069,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852099142.065, "dur": 34.768, + "args": { + "External id": 1434070,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852099238.646, "dur": 122.770, + "args": { + "External id": 1434071,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852099269.514, "dur": 88.191, + "args": { + "External id": 1434072,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4055, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852099280.157, "dur": 72.746, + "args": { + "External id": 1434073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852099378.935, "dur": 1.753, + "args": { + "External id": 1434074,"Record function id": 0, "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": 4057, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852099463.782, "dur": 1849.082, + "args": { + "External id": 1434075,"Sequence number": 15348680, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4058 + } + }, + { + "ph": "f", "id": 202, "pid": 2338706, "tid": 2379422, "ts": 6413852099463.782, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852099580.774, "dur": 103.749, + "args": { + "External id": 1434076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852099726.465, "dur": 41.934, + "args": { + "External id": 1434077,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852099785.898, "dur": 47.514, + "args": { + "External id": 1434078,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852099845.561, "dur": 30.899, + "args": { + "External id": 1434079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852099882.449, "dur": 31.234, + "args": { + "External id": 1434080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852099919.433, "dur": 26.526, + "args": { + "External id": 1434081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852099953.805, "dur": 48.561, + "args": { + "External id": 1434082,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852100033.686, "dur": 61.626, + "args": { + "External id": 1434083,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852100120.087, "dur": 30.829, + "args": { + "External id": 1434084,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852100175.743, "dur": 21.223, + "args": { + "External id": 1434085,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852100211.481, "dur": 15.592, + "args": { + "External id": 1434086,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100236.066, "dur": 41.556, + "args": { + "External id": 1434087,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100281.102, "dur": 32.273, + "args": { + "External id": 1434088,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852100346.339, "dur": 247.265, + "args": { + "External id": 1434089,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852100427.703, "dur": 6.345, + "args": { + "External id": 1434090,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852100436.143, "dur": 2.987, + "args": { + "External id": 1434091,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852100440.489, "dur": 1.901, + "args": { + "External id": 1434092,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852100443.466, "dur": 1.631, + "args": { + "External id": 1434093,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852100486.477, "dur": 4.877, + "args": { + "External id": 1434094,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852100488.657, "dur": 2.544, + "args": { + "External id": 1434095,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852100493.599, "dur": 34.958, + "args": { + "External id": 1434096,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852100501.316, "dur": 3.637, + "args": { + "External id": 1434097,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852100530.325, "dur": 1.617, + "args": { + "External id": 1434098,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852100531.263, "dur": 0.566, + "args": { + "External id": 1434099,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852100533.043, "dur": 14.406, + "args": { + "External id": 1434100,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852100535.247, "dur": 0.955, + "args": { + "External id": 1434101,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852100632.979, "dur": 24.865, + "args": { + "External id": 1434102,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852100674.184, "dur": 15.901, + "args": { + "External id": 1434103,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100697.275, "dur": 37.111, + "args": { + "External id": 1434104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100740.628, "dur": 36.834, + "args": { + "External id": 1434105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100786.702, "dur": 21.351, + "args": { + "External id": 1434106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100813.570, "dur": 30.298, + "args": { + "External id": 1434107,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100850.808, "dur": 26.630, + "args": { + "External id": 1434108,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852100884.415, "dur": 29.404, + "args": { + "External id": 1434109,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852100945.756, "dur": 46.275, + "args": { + "External id": 1434110,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852101018.686, "dur": 25.870, + "args": { + "External id": 1434111,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852101097.424, "dur": 21.632, + "args": { + "External id": 1434112,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852101222.799, "dur": 18.518, + "args": { + "External id": 1434113,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852101257.684, "dur": 18.656, + "args": { + "External id": 1434114,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101365.565, "dur": 16.391, + "args": { + "External id": 1434115,"Record function id": 0, "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101369.442, "dur": 11.482, + "args": { + "External id": 1434116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101373.854, "dur": 6.071, + "args": { + "External id": 1434117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101375.464, "dur": 4.378, + "args": { + "External id": 1434118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101385.829, "dur": 4.985, + "args": { + "External id": 1434119,"Record function id": 0, "Ev Idx": 4102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101387.839, "dur": 2.559, + "args": { + "External id": 1434120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101388.440, "dur": 1.349, + "args": { + "External id": 1434121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101388.991, "dur": 0.719, + "args": { + "External id": 1434122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101393.998, "dur": 7.199, + "args": { + "External id": 1434123,"Record function id": 0, "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101395.672, "dur": 5.093, + "args": { + "External id": 1434124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101396.634, "dur": 3.686, + "args": { + "External id": 1434125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101396.943, "dur": 3.317, + "args": { + "External id": 1434126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101404.349, "dur": 4.640, + "args": { + "External id": 1434127,"Record function id": 0, "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101405.749, "dur": 2.756, + "args": { + "External id": 1434128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101406.458, "dur": 1.360, + "args": { + "External id": 1434129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101407.000, "dur": 0.705, + "args": { + "External id": 1434130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101412.078, "dur": 4.345, + "args": { + "External id": 1434131,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101413.378, "dur": 2.586, + "args": { + "External id": 1434132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101413.876, "dur": 1.457, + "args": { + "External id": 1434133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101414.522, "dur": 0.734, + "args": { + "External id": 1434134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101419.594, "dur": 3.784, + "args": { + "External id": 1434135,"Record function id": 0, "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101421.035, "dur": 1.876, + "args": { + "External id": 1434136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101421.518, "dur": 0.957, + "args": { + "External id": 1434137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101421.819, "dur": 0.582, + "args": { + "External id": 1434138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101426.607, "dur": 4.071, + "args": { + "External id": 1434139,"Record function id": 0, "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101428.254, "dur": 1.980, + "args": { + "External id": 1434140,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101428.692, "dur": 1.125, + "args": { + "External id": 1434141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101429.049, "dur": 0.703, + "args": { + "External id": 1434142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101433.878, "dur": 6.146, + "args": { + "External id": 1434143,"Record function id": 0, "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101435.310, "dur": 4.299, + "args": { + "External id": 1434144,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101435.785, "dur": 3.274, + "args": { + "External id": 1434145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101438.239, "dur": 0.731, + "args": { + "External id": 1434146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101443.192, "dur": 3.699, + "args": { + "External id": 1434147,"Record function id": 0, "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852101444.555, "dur": 1.890, + "args": { + "External id": 1434148,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101445.013, "dur": 0.994, + "args": { + "External id": 1434149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852101445.283, "dur": 0.634, + "args": { + "External id": 1434150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852101451.119, "dur": 67845.382, + "args": { + "External id": 1434151,"Record function id": 0, "Sequence number": 15348679, "Fwd thread id": 1, "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852101452.609, "dur": 67833.554, + "args": { + "External id": 1434152,"Sequence number": 15348679, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4135 + } + }, + { + "ph": "f", "id": 203, "pid": 2338706, "tid": 2379422, "ts": 6413852101452.609, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413852101483.056, "dur": 36.996, + "args": { + "External id": 1434153,"Record function id": 0, "Ev Idx": 4136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413852101527.869, "dur": 67.836, + "args": { + "External id": 1434154,"Record function id": 0, "Ev Idx": 4137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413852101601.290, "dur": 67676.684, + "args": { + "External id": 1434155,"Record function id": 0, "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852101689.912, "dur": 7.449, + "args": { + "External id": 1434156,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852101707.432, "dur": 7.033, + "args": { + "External id": 1434157,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852101728.201, "dur": 66583.295, + "args": { + "External id": 1434158,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852101741.885, "dur": 66556.374, + "args": { + "External id": 1434159,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852101851.957, "dur": 17.695, + "args": { + "External id": 1434160,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852101889.839, "dur": 66359.542, + "args": { + "External id": 1434161,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852101895.244, "dur": 66353.098, + "args": { + "External id": 1434162,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852101899.955, "dur": 9.328, + "args": { + "External id": 1434163,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852101911.519, "dur": 66331.763, + "args": { + "External id": 1434164,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852168449.895, "dur": 13.498, + "args": { + "External id": 1434165,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852168453.752, "dur": 9.353, + "args": { + "External id": 1434166,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852168493.861, "dur": 423.120, + "args": { + "External id": 1434167,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852168527.444, "dur": 384.573, + "args": { + "External id": 1434168,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4151, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852168539.587, "dur": 366.010, + "args": { + "External id": 1434169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852168942.017, "dur": 2.448, + "args": { + "External id": 1434170,"Record function id": 0, "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": 4153, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169028.331, "dur": 7.277, + "args": { + "External id": 1434171,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169116.635, "dur": 2.162, + "args": { + "External id": 1434172,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169135.648, "dur": 3.340, + "args": { + "External id": 1434173,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169151.194, "dur": 0.956, + "args": { + "External id": 1434174,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169162.888, "dur": 0.778, + "args": { + "External id": 1434175,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169174.787, "dur": 0.759, + "args": { + "External id": 1434176,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169185.859, "dur": 3.640, + "args": { + "External id": 1434177,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169199.700, "dur": 2.197, + "args": { + "External id": 1434178,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169213.442, "dur": 0.946, + "args": { + "External id": 1434179,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852169314.848, "dur": 3053.393, + "args": { + "External id": 1434180,"Record function id": 0, "Ev Idx": 4163 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413852169334.808, "dur": 1135.458, + "args": { + "External id": 1434181,"Record function id": 0, "Ev Idx": 4164 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413852169349.524, "dur": 337.942, + "args": { + "External id": 1434182,"Record function id": 0, "Ev Idx": 4165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169444.503, "dur": 4.355, + "args": { + "External id": 1434183,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169451.953, "dur": 0.742, + "args": { + "External id": 1434184,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169454.619, "dur": 2.632, + "args": { + "External id": 1434185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169459.173, "dur": 0.806, + "args": { + "External id": 1434186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169461.720, "dur": 0.795, + "args": { + "External id": 1434187,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169464.038, "dur": 0.670, + "args": { + "External id": 1434188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169466.371, "dur": 1.983, + "args": { + "External id": 1434189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169472.172, "dur": 0.698, + "args": { + "External id": 1434190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169477.336, "dur": 0.830, + "args": { + "External id": 1434191,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852169479.930, "dur": 0.681, + "args": { + "External id": 1434192,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852169499.141, "dur": 160.002, + "args": { + "External id": 1434193,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852169518.225, "dur": 136.482, + "args": { + "External id": 1434194,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852169536.010, "dur": 17.549, + "args": { + "External id": 1434195,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852169557.331, "dur": 64.300, + "args": { + "External id": 1434196,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852169560.042, "dur": 61.255, + "args": { + "External id": 1434197,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169564.799, "dur": 5.376, + "args": { + "External id": 1434198,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852169572.019, "dur": 48.627, + "args": { + "External id": 1434199,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4182 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 2338706, "tid": 2379422, + "ts": 6413852169779.665, "dur": 682.400, + "args": { + "External id": 1434200,"Record function id": 0, "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413852169797.286, "dur": 651.966, + "args": { + "External id": 1434201,"Record function id": 0, "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852169857.674, "dur": 4.909, + "args": { + "External id": 1434202,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852169878.270, "dur": 31.407, + "args": { + "External id": 1434203,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169883.494, "dur": 1.434, + "args": { + "External id": 1434204,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169887.148, "dur": 1.431, + "args": { + "External id": 1434205,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169889.879, "dur": 0.512, + "args": { + "External id": 1434206,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169891.784, "dur": 0.411, + "args": { + "External id": 1434207,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169894.687, "dur": 0.435, + "args": { + "External id": 1434208,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169896.734, "dur": 2.277, + "args": { + "External id": 1434209,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169900.911, "dur": 0.305, + "args": { + "External id": 1434210,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169902.866, "dur": 0.399, + "args": { + "External id": 1434211,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852169904.553, "dur": 0.263, + "args": { + "External id": 1434212,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852169920.982, "dur": 44.060, + "args": { + "External id": 1434213,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852170019.476, "dur": 163.073, + "args": { + "External id": 1434214,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852170030.675, "dur": 4.910, + "args": { + "External id": 1434215,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852170041.393, "dur": 11.152, + "args": { + "External id": 1434216,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852170045.707, "dur": 6.411, + "args": { + "External id": 1434217,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170049.738, "dur": 0.878, + "args": { + "External id": 1434218,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852170097.090, "dur": 27.847, + "args": { + "External id": 1434219,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170099.790, "dur": 0.524, + "args": { + "External id": 1434220,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170102.880, "dur": 0.382, + "args": { + "External id": 1434221,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170104.975, "dur": 2.385, + "args": { + "External id": 1434222,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170109.084, "dur": 0.671, + "args": { + "External id": 1434223,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170111.410, "dur": 0.477, + "args": { + "External id": 1434224,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170113.688, "dur": 0.375, + "args": { + "External id": 1434225,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170115.830, "dur": 0.274, + "args": { + "External id": 1434226,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170117.702, "dur": 0.335, + "args": { + "External id": 1434227,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852170119.589, "dur": 0.308, + "args": { + "External id": 1434228,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852170136.409, "dur": 37.558, + "args": { + "External id": 1434229,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852170231.395, "dur": 144.031, + "args": { + "External id": 1434230,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852170262.166, "dur": 109.759, + "args": { + "External id": 1434231,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4214, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852170291.282, "dur": 76.223, + "args": { + "External id": 1434232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852170394.103, "dur": 2.012, + "args": { + "External id": 1434233,"Record function id": 0, "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": 4216, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852170477.848, "dur": 1867.249, + "args": { + "External id": 1434234,"Sequence number": 15348678, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4217 + } + }, + { + "ph": "f", "id": 204, "pid": 2338706, "tid": 2379422, "ts": 6413852170477.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852170593.449, "dur": 106.556, + "args": { + "External id": 1434235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852170742.512, "dur": 44.616, + "args": { + "External id": 1434236,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852170804.614, "dur": 48.491, + "args": { + "External id": 1434237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852170865.596, "dur": 31.403, + "args": { + "External id": 1434238,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852170903.449, "dur": 32.422, + "args": { + "External id": 1434239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852170942.051, "dur": 27.120, + "args": { + "External id": 1434240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852170998.393, "dur": 33.915, + "args": { + "External id": 1434241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852171099.186, "dur": 29.528, + "args": { + "External id": 1434242,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852171149.439, "dur": 28.087, + "args": { + "External id": 1434243,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852171207.395, "dur": 18.882, + "args": { + "External id": 1434244,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852171240.468, "dur": 17.261, + "args": { + "External id": 1434245,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171265.761, "dur": 45.287, + "args": { + "External id": 1434246,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171314.927, "dur": 33.797, + "args": { + "External id": 1434247,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852171381.368, "dur": 247.622, + "args": { + "External id": 1434248,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852171460.057, "dur": 6.419, + "args": { + "External id": 1434249,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852171468.825, "dur": 2.529, + "args": { + "External id": 1434250,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852171472.804, "dur": 1.791, + "args": { + "External id": 1434251,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852171476.376, "dur": 1.977, + "args": { + "External id": 1434252,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852171523.944, "dur": 8.779, + "args": { + "External id": 1434253,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852171528.610, "dur": 3.950, + "args": { + "External id": 1434254,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852171534.803, "dur": 33.659, + "args": { + "External id": 1434255,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852171541.309, "dur": 3.241, + "args": { + "External id": 1434256,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852171569.893, "dur": 1.785, + "args": { + "External id": 1434257,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852171571.072, "dur": 0.502, + "args": { + "External id": 1434258,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852171572.567, "dur": 14.084, + "args": { + "External id": 1434259,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852171574.757, "dur": 0.487, + "args": { + "External id": 1434260,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852171669.374, "dur": 26.177, + "args": { + "External id": 1434261,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852171715.399, "dur": 17.631, + "args": { + "External id": 1434262,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171740.996, "dur": 39.773, + "args": { + "External id": 1434263,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171787.168, "dur": 37.484, + "args": { + "External id": 1434264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171834.076, "dur": 21.886, + "args": { + "External id": 1434265,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171872.046, "dur": 45.042, + "args": { + "External id": 1434266,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171930.095, "dur": 32.554, + "args": { + "External id": 1434267,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852171969.382, "dur": 54.845, + "args": { + "External id": 1434268,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852172097.260, "dur": 28.340, + "args": { + "External id": 1434269,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852172145.297, "dur": 24.564, + "args": { + "External id": 1434270,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852172189.465, "dur": 16.219, + "args": { + "External id": 1434271,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852172263.676, "dur": 15.476, + "args": { + "External id": 1434272,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852172298.184, "dur": 15.867, + "args": { + "External id": 1434273,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172392.352, "dur": 17.696, + "args": { + "External id": 1434274,"Record function id": 0, "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172396.239, "dur": 12.864, + "args": { + "External id": 1434275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172400.691, "dur": 7.300, + "args": { + "External id": 1434276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172402.351, "dur": 5.540, + "args": { + "External id": 1434277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172414.012, "dur": 5.219, + "args": { + "External id": 1434278,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172415.794, "dur": 2.978, + "args": { + "External id": 1434279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172416.688, "dur": 1.621, + "args": { + "External id": 1434280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172417.209, "dur": 1.009, + "args": { + "External id": 1434281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172422.527, "dur": 7.283, + "args": { + "External id": 1434282,"Record function id": 0, "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172424.483, "dur": 4.884, + "args": { + "External id": 1434283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172425.131, "dur": 3.639, + "args": { + "External id": 1434284,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172425.678, "dur": 2.998, + "args": { + "External id": 1434285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172433.046, "dur": 5.039, + "args": { + "External id": 1434286,"Record function id": 0, "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172434.691, "dur": 2.941, + "args": { + "External id": 1434287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172435.511, "dur": 1.413, + "args": { + "External id": 1434288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172436.150, "dur": 0.714, + "args": { + "External id": 1434289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172441.330, "dur": 3.860, + "args": { + "External id": 1434290,"Record function id": 0, "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172442.487, "dur": 2.290, + "args": { + "External id": 1434291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172443.124, "dur": 1.046, + "args": { + "External id": 1434292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172443.443, "dur": 0.664, + "args": { + "External id": 1434293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172448.245, "dur": 4.953, + "args": { + "External id": 1434294,"Record function id": 0, "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172450.056, "dur": 2.708, + "args": { + "External id": 1434295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172450.618, "dur": 1.565, + "args": { + "External id": 1434296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172451.471, "dur": 0.638, + "args": { + "External id": 1434297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172456.584, "dur": 3.889, + "args": { + "External id": 1434298,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172457.901, "dur": 2.174, + "args": { + "External id": 1434299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172458.505, "dur": 0.905, + "args": { + "External id": 1434300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172458.766, "dur": 0.579, + "args": { + "External id": 1434301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172463.610, "dur": 4.305, + "args": { + "External id": 1434302,"Record function id": 0, "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172465.204, "dur": 2.303, + "args": { + "External id": 1434303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172465.691, "dur": 1.270, + "args": { + "External id": 1434304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172466.071, "dur": 0.823, + "args": { + "External id": 1434305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172471.026, "dur": 6.199, + "args": { + "External id": 1434306,"Record function id": 0, "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852172472.410, "dur": 4.415, + "args": { + "External id": 1434307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172473.134, "dur": 3.279, + "args": { + "External id": 1434308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852172475.761, "dur": 0.585, + "args": { + "External id": 1434309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852172481.819, "dur": 60551.115, + "args": { + "External id": 1434310,"Record function id": 0, "Sequence number": 15348677, "Fwd thread id": 1, "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852172483.536, "dur": 60538.173, + "args": { + "External id": 1434311,"Sequence number": 15348677, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4294 + } + }, + { + "ph": "f", "id": 205, "pid": 2338706, "tid": 2379422, "ts": 6413852172483.536, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413852172513.598, "dur": 40.167, + "args": { + "External id": 1434312,"Record function id": 0, "Ev Idx": 4295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413852172562.005, "dur": 69.115, + "args": { + "External id": 1434313,"Record function id": 0, "Ev Idx": 4296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413852172639.512, "dur": 60372.688, + "args": { + "External id": 1434314,"Record function id": 0, "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852172735.337, "dur": 7.644, + "args": { + "External id": 1434315,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852172753.135, "dur": 6.805, + "args": { + "External id": 1434316,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852172774.619, "dur": 59468.277, + "args": { + "External id": 1434317,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852172788.827, "dur": 59440.479, + "args": { + "External id": 1434318,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852172886.823, "dur": 17.544, + "args": { + "External id": 1434319,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852172927.754, "dur": 59253.829, + "args": { + "External id": 1434320,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852172930.550, "dur": 59249.658, + "args": { + "External id": 1434321,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852172935.413, "dur": 10.793, + "args": { + "External id": 1434322,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852172950.472, "dur": 59224.234, + "args": { + "External id": 1434323,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852232352.755, "dur": 12.743, + "args": { + "External id": 1434324,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852232356.468, "dur": 8.647, + "args": { + "External id": 1434325,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852232394.848, "dur": 311.547, + "args": { + "External id": 1434326,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852232429.052, "dur": 272.481, + "args": { + "External id": 1434327,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4310, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852232442.899, "dur": 253.128, + "args": { + "External id": 1434328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852232727.507, "dur": 1.957, + "args": { + "External id": 1434329,"Record function id": 0, "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": 4312, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232784.980, "dur": 6.607, + "args": { + "External id": 1434330,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232836.167, "dur": 1.523, + "args": { + "External id": 1434331,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232853.861, "dur": 3.830, + "args": { + "External id": 1434332,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232870.167, "dur": 1.149, + "args": { + "External id": 1434333,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232884.678, "dur": 0.931, + "args": { + "External id": 1434334,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232896.245, "dur": 0.778, + "args": { + "External id": 1434335,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232908.055, "dur": 2.842, + "args": { + "External id": 1434336,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232921.385, "dur": 2.447, + "args": { + "External id": 1434337,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852232933.691, "dur": 0.734, + "args": { + "External id": 1434338,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852233049.631, "dur": 2974.888, + "args": { + "External id": 1434339,"Record function id": 0, "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413852233105.526, "dur": 1132.893, + "args": { + "External id": 1434340,"Record function id": 0, "Ev Idx": 4323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413852233122.265, "dur": 348.096, + "args": { + "External id": 1434341,"Record function id": 0, "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233222.949, "dur": 4.940, + "args": { + "External id": 1434342,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233231.086, "dur": 0.906, + "args": { + "External id": 1434343,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233234.003, "dur": 3.437, + "args": { + "External id": 1434344,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233239.204, "dur": 0.627, + "args": { + "External id": 1434345,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233243.416, "dur": 0.992, + "args": { + "External id": 1434346,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233245.787, "dur": 0.875, + "args": { + "External id": 1434347,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233248.146, "dur": 2.487, + "args": { + "External id": 1434348,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233252.087, "dur": 0.869, + "args": { + "External id": 1434349,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233256.339, "dur": 0.908, + "args": { + "External id": 1434350,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852233258.627, "dur": 1.116, + "args": { + "External id": 1434351,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852233278.314, "dur": 160.616, + "args": { + "External id": 1434352,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852233295.492, "dur": 138.421, + "args": { + "External id": 1434353,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852233316.149, "dur": 19.078, + "args": { + "External id": 1434354,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852233339.114, "dur": 66.787, + "args": { + "External id": 1434355,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852233344.018, "dur": 61.581, + "args": { + "External id": 1434356,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233348.680, "dur": 5.480, + "args": { + "External id": 1434357,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852233355.817, "dur": 49.185, + "args": { + "External id": 1434358,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 2338706, "tid": 2379422, + "ts": 6413852233565.323, "dur": 665.320, + "args": { + "External id": 1434359,"Record function id": 0, "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413852233582.142, "dur": 635.082, + "args": { + "External id": 1434360,"Record function id": 0, "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852233645.172, "dur": 4.944, + "args": { + "External id": 1434361,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852233666.223, "dur": 34.513, + "args": { + "External id": 1434362,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233671.913, "dur": 2.660, + "args": { + "External id": 1434363,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233676.779, "dur": 0.417, + "args": { + "External id": 1434364,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233678.704, "dur": 0.607, + "args": { + "External id": 1434365,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233682.317, "dur": 0.421, + "args": { + "External id": 1434366,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233684.136, "dur": 0.422, + "args": { + "External id": 1434367,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233686.098, "dur": 2.630, + "args": { + "External id": 1434368,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233691.076, "dur": 0.354, + "args": { + "External id": 1434369,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233693.123, "dur": 0.381, + "args": { + "External id": 1434370,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233694.985, "dur": 1.105, + "args": { + "External id": 1434371,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852233711.806, "dur": 45.313, + "args": { + "External id": 1434372,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852233787.854, "dur": 116.239, + "args": { + "External id": 1434373,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852233797.006, "dur": 3.939, + "args": { + "External id": 1434374,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852233806.589, "dur": 10.140, + "args": { + "External id": 1434375,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852233810.691, "dur": 5.633, + "args": { + "External id": 1434376,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233814.484, "dur": 0.746, + "args": { + "External id": 1434377,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852233823.727, "dur": 29.358, + "args": { + "External id": 1434378,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233825.971, "dur": 0.541, + "args": { + "External id": 1434379,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233828.396, "dur": 0.345, + "args": { + "External id": 1434380,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233833.261, "dur": 3.447, + "args": { + "External id": 1434381,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233838.416, "dur": 0.349, + "args": { + "External id": 1434382,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233839.972, "dur": 0.343, + "args": { + "External id": 1434383,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233842.989, "dur": 0.437, + "args": { + "External id": 1434384,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233844.754, "dur": 0.371, + "args": { + "External id": 1434385,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233846.743, "dur": 0.461, + "args": { + "External id": 1434386,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852233848.554, "dur": 0.270, + "args": { + "External id": 1434387,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852233865.902, "dur": 30.642, + "args": { + "External id": 1434388,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852233949.923, "dur": 184.594, + "args": { + "External id": 1434389,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852234002.507, "dur": 127.356, + "args": { + "External id": 1434390,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4373, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852234012.708, "dur": 111.963, + "args": { + "External id": 1434391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852234155.945, "dur": 2.030, + "args": { + "External id": 1434392,"Record function id": 0, "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": 4375, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852234246.162, "dur": 1754.821, + "args": { + "External id": 1434393,"Sequence number": 15348676, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4376 + } + }, + { + "ph": "f", "id": 206, "pid": 2338706, "tid": 2379422, "ts": 6413852234246.162, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234363.975, "dur": 105.856, + "args": { + "External id": 1434394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852234535.079, "dur": 43.395, + "args": { + "External id": 1434395,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234596.262, "dur": 51.309, + "args": { + "External id": 1434396,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234659.731, "dur": 32.583, + "args": { + "External id": 1434397,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234698.085, "dur": 33.366, + "args": { + "External id": 1434398,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234737.781, "dur": 26.701, + "args": { + "External id": 1434399,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234771.115, "dur": 29.148, + "args": { + "External id": 1434400,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852234829.046, "dur": 21.076, + "args": { + "External id": 1434401,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852234869.063, "dur": 30.841, + "args": { + "External id": 1434402,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852234923.650, "dur": 18.373, + "args": { + "External id": 1434403,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852234955.568, "dur": 13.762, + "args": { + "External id": 1434404,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852234996.246, "dur": 42.713, + "args": { + "External id": 1434405,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235042.966, "dur": 67.991, + "args": { + "External id": 1434406,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852235149.027, "dur": 246.720, + "args": { + "External id": 1434407,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852235229.744, "dur": 5.906, + "args": { + "External id": 1434408,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852235237.744, "dur": 2.726, + "args": { + "External id": 1434409,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852235242.003, "dur": 1.802, + "args": { + "External id": 1434410,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852235245.143, "dur": 2.840, + "args": { + "External id": 1434411,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852235293.169, "dur": 5.065, + "args": { + "External id": 1434412,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852235295.160, "dur": 2.891, + "args": { + "External id": 1434413,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852235300.321, "dur": 34.398, + "args": { + "External id": 1434414,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852235306.315, "dur": 3.681, + "args": { + "External id": 1434415,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852235336.377, "dur": 1.843, + "args": { + "External id": 1434416,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852235337.574, "dur": 0.579, + "args": { + "External id": 1434417,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852235339.214, "dur": 14.048, + "args": { + "External id": 1434418,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852235341.371, "dur": 0.430, + "args": { + "External id": 1434419,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852235437.253, "dur": 27.159, + "args": { + "External id": 1434420,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852235483.806, "dur": 17.080, + "args": { + "External id": 1434421,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235508.639, "dur": 42.071, + "args": { + "External id": 1434422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235557.222, "dur": 37.018, + "args": { + "External id": 1434423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235604.121, "dur": 19.747, + "args": { + "External id": 1434424,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235629.432, "dur": 30.469, + "args": { + "External id": 1434425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235666.669, "dur": 30.641, + "args": { + "External id": 1434426,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852235704.518, "dur": 29.163, + "args": { + "External id": 1434427,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852235758.139, "dur": 38.607, + "args": { + "External id": 1434428,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852235821.075, "dur": 27.258, + "args": { + "External id": 1434429,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852235865.594, "dur": 16.753, + "args": { + "External id": 1434430,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852235903.596, "dur": 17.294, + "args": { + "External id": 1434431,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852235933.858, "dur": 15.263, + "args": { + "External id": 1434432,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236047.773, "dur": 63.925, + "args": { + "External id": 1434433,"Record function id": 0, "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236051.127, "dur": 58.802, + "args": { + "External id": 1434434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236102.192, "dur": 6.260, + "args": { + "External id": 1434435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236103.778, "dur": 4.405, + "args": { + "External id": 1434436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236118.045, "dur": 6.690, + "args": { + "External id": 1434437,"Record function id": 0, "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236120.255, "dur": 4.014, + "args": { + "External id": 1434438,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236121.559, "dur": 2.002, + "args": { + "External id": 1434439,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236122.222, "dur": 1.261, + "args": { + "External id": 1434440,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236128.060, "dur": 6.782, + "args": { + "External id": 1434441,"Record function id": 0, "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236129.525, "dur": 4.866, + "args": { + "External id": 1434442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236129.979, "dur": 3.976, + "args": { + "External id": 1434443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236130.591, "dur": 3.264, + "args": { + "External id": 1434444,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236138.041, "dur": 4.419, + "args": { + "External id": 1434445,"Record function id": 0, "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236139.304, "dur": 2.715, + "args": { + "External id": 1434446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236139.944, "dur": 1.404, + "args": { + "External id": 1434447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236140.439, "dur": 0.836, + "args": { + "External id": 1434448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236145.837, "dur": 4.294, + "args": { + "External id": 1434449,"Record function id": 0, "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236147.216, "dur": 2.463, + "args": { + "External id": 1434450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236147.899, "dur": 1.341, + "args": { + "External id": 1434451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236148.499, "dur": 0.666, + "args": { + "External id": 1434452,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236153.200, "dur": 3.875, + "args": { + "External id": 1434453,"Record function id": 0, "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236154.549, "dur": 2.088, + "args": { + "External id": 1434454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236154.981, "dur": 1.244, + "args": { + "External id": 1434455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236155.365, "dur": 0.785, + "args": { + "External id": 1434456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236160.471, "dur": 5.597, + "args": { + "External id": 1434457,"Record function id": 0, "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236161.641, "dur": 4.000, + "args": { + "External id": 1434458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236162.061, "dur": 2.958, + "args": { + "External id": 1434459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236164.339, "dur": 0.585, + "args": { + "External id": 1434460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236169.201, "dur": 3.984, + "args": { + "External id": 1434461,"Record function id": 0, "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236170.709, "dur": 2.069, + "args": { + "External id": 1434462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236171.317, "dur": 1.023, + "args": { + "External id": 1434463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236171.640, "dur": 0.610, + "args": { + "External id": 1434464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236176.303, "dur": 3.474, + "args": { + "External id": 1434465,"Record function id": 0, "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852236177.335, "dur": 2.040, + "args": { + "External id": 1434466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236177.787, "dur": 1.207, + "args": { + "External id": 1434467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852236178.312, "dur": 0.616, + "args": { + "External id": 1434468,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852236184.181, "dur": 71503.429, + "args": { + "External id": 1434469,"Record function id": 0, "Sequence number": 15348675, "Fwd thread id": 1, "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852236186.079, "dur": 71492.089, + "args": { + "External id": 1434470,"Sequence number": 15348675, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4453 + } + }, + { + "ph": "f", "id": 207, "pid": 2338706, "tid": 2379422, "ts": 6413852236186.079, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413852236218.205, "dur": 39.929, + "args": { + "External id": 1434471,"Record function id": 0, "Ev Idx": 4454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413852236265.882, "dur": 69.222, + "args": { + "External id": 1434472,"Record function id": 0, "Ev Idx": 4455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413852236340.833, "dur": 71329.189, + "args": { + "External id": 1434473,"Record function id": 0, "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852236434.525, "dur": 7.592, + "args": { + "External id": 1434474,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852236451.726, "dur": 6.795, + "args": { + "External id": 1434475,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852236474.008, "dur": 70293.477, + "args": { + "External id": 1434476,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852236490.572, "dur": 70263.458, + "args": { + "External id": 1434477,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852236584.786, "dur": 17.166, + "args": { + "External id": 1434478,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852236621.902, "dur": 70086.658, + "args": { + "External id": 1434479,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852236624.916, "dur": 70082.478, + "args": { + "External id": 1434480,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852236630.553, "dur": 9.680, + "args": { + "External id": 1434481,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852236642.477, "dur": 70059.779, + "args": { + "External id": 1434482,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852306877.504, "dur": 12.286, + "args": { + "External id": 1434483,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852306880.952, "dur": 8.482, + "args": { + "External id": 1434484,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852306921.535, "dur": 443.436, + "args": { + "External id": 1434485,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852306955.715, "dur": 403.331, + "args": { + "External id": 1434486,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4469, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852306968.362, "dur": 384.682, + "args": { + "External id": 1434487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852307392.199, "dur": 2.116, + "args": { + "External id": 1434488,"Record function id": 0, "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": 4471, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307458.013, "dur": 6.897, + "args": { + "External id": 1434489,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307510.427, "dur": 1.552, + "args": { + "External id": 1434490,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307528.735, "dur": 3.450, + "args": { + "External id": 1434491,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307543.808, "dur": 1.223, + "args": { + "External id": 1434492,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307558.173, "dur": 0.995, + "args": { + "External id": 1434493,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307569.902, "dur": 0.734, + "args": { + "External id": 1434494,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307581.378, "dur": 3.541, + "args": { + "External id": 1434495,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307595.801, "dur": 2.201, + "args": { + "External id": 1434496,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307608.376, "dur": 0.735, + "args": { + "External id": 1434497,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852307702.860, "dur": 3041.887, + "args": { + "External id": 1434498,"Record function id": 0, "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413852307725.051, "dur": 1115.373, + "args": { + "External id": 1434499,"Record function id": 0, "Ev Idx": 4482 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413852307739.664, "dur": 391.298, + "args": { + "External id": 1434500,"Record function id": 0, "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307832.583, "dur": 3.834, + "args": { + "External id": 1434501,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307839.523, "dur": 0.755, + "args": { + "External id": 1434502,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307842.122, "dur": 2.593, + "args": { + "External id": 1434503,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307846.682, "dur": 1.058, + "args": { + "External id": 1434504,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307849.405, "dur": 0.818, + "args": { + "External id": 1434505,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307851.714, "dur": 0.930, + "args": { + "External id": 1434506,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307854.195, "dur": 2.659, + "args": { + "External id": 1434507,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307860.554, "dur": 0.808, + "args": { + "External id": 1434508,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307862.833, "dur": 1.197, + "args": { + "External id": 1434509,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852307865.846, "dur": 0.914, + "args": { + "External id": 1434510,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852307884.930, "dur": 210.393, + "args": { + "External id": 1434511,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852307901.727, "dur": 187.826, + "args": { + "External id": 1434512,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852307920.642, "dur": 17.208, + "args": { + "External id": 1434513,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852307944.107, "dur": 83.879, + "args": { + "External id": 1434514,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852307946.977, "dur": 80.619, + "args": { + "External id": 1434515,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852307950.884, "dur": 5.190, + "args": { + "External id": 1434516,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852307957.850, "dur": 68.699, + "args": { + "External id": 1434517,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 2338706, "tid": 2379422, + "ts": 6413852308228.037, "dur": 604.771, + "args": { + "External id": 1434518,"Record function id": 0, "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413852308247.374, "dur": 572.057, + "args": { + "External id": 1434519,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852308314.702, "dur": 6.427, + "args": { + "External id": 1434520,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852308337.774, "dur": 35.689, + "args": { + "External id": 1434521,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308343.159, "dur": 3.382, + "args": { + "External id": 1434522,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308348.587, "dur": 0.362, + "args": { + "External id": 1434523,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308350.821, "dur": 0.444, + "args": { + "External id": 1434524,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308354.425, "dur": 0.271, + "args": { + "External id": 1434525,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308356.090, "dur": 0.365, + "args": { + "External id": 1434526,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308357.981, "dur": 2.672, + "args": { + "External id": 1434527,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308363.499, "dur": 0.353, + "args": { + "External id": 1434528,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308365.435, "dur": 0.280, + "args": { + "External id": 1434529,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308367.032, "dur": 1.219, + "args": { + "External id": 1434530,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852308384.357, "dur": 46.115, + "args": { + "External id": 1434531,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852308461.743, "dur": 115.546, + "args": { + "External id": 1434532,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852308471.563, "dur": 3.332, + "args": { + "External id": 1434533,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852308480.380, "dur": 10.755, + "args": { + "External id": 1434534,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852308484.729, "dur": 5.968, + "args": { + "External id": 1434535,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308488.747, "dur": 0.642, + "args": { + "External id": 1434536,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852308497.953, "dur": 27.478, + "args": { + "External id": 1434537,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308500.789, "dur": 0.339, + "args": { + "External id": 1434538,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308503.036, "dur": 0.399, + "args": { + "External id": 1434539,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308504.894, "dur": 3.271, + "args": { + "External id": 1434540,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308509.536, "dur": 0.542, + "args": { + "External id": 1434541,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308511.798, "dur": 0.397, + "args": { + "External id": 1434542,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308514.976, "dur": 0.333, + "args": { + "External id": 1434543,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308516.798, "dur": 0.409, + "args": { + "External id": 1434544,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308518.457, "dur": 0.414, + "args": { + "External id": 1434545,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852308520.976, "dur": 0.399, + "args": { + "External id": 1434546,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852308535.596, "dur": 33.914, + "args": { + "External id": 1434547,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852308623.901, "dur": 123.407, + "args": { + "External id": 1434548,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852308654.519, "dur": 89.383, + "args": { + "External id": 1434549,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4532, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852308664.304, "dur": 75.287, + "args": { + "External id": 1434550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852308766.338, "dur": 2.044, + "args": { + "External id": 1434551,"Record function id": 0, "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": 4534, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852308847.481, "dur": 1872.694, + "args": { + "External id": 1434552,"Sequence number": 15348674, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4535 + } + }, + { + "ph": "f", "id": 208, "pid": 2338706, "tid": 2379422, "ts": 6413852308847.481, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852308958.099, "dur": 169.616, + "args": { + "External id": 1434553,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852309179.393, "dur": 43.063, + "args": { + "External id": 1434554,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309268.417, "dur": 58.085, + "args": { + "External id": 1434555,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309340.227, "dur": 32.898, + "args": { + "External id": 1434556,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309379.568, "dur": 31.509, + "args": { + "External id": 1434557,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309417.821, "dur": 28.418, + "args": { + "External id": 1434558,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309452.756, "dur": 28.222, + "args": { + "External id": 1434559,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852309512.086, "dur": 23.720, + "args": { + "External id": 1434560,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852309556.272, "dur": 27.665, + "args": { + "External id": 1434561,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852309606.821, "dur": 17.872, + "args": { + "External id": 1434562,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852309638.739, "dur": 14.240, + "args": { + "External id": 1434563,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309660.016, "dur": 35.237, + "args": { + "External id": 1434564,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852309698.596, "dur": 32.800, + "args": { + "External id": 1434565,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852309763.525, "dur": 323.811, + "args": { + "External id": 1434566,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852309842.027, "dur": 5.771, + "args": { + "External id": 1434567,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852309850.321, "dur": 2.200, + "args": { + "External id": 1434568,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852309853.941, "dur": 1.613, + "args": { + "External id": 1434569,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852309856.847, "dur": 3.378, + "args": { + "External id": 1434570,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852309905.322, "dur": 10.633, + "args": { + "External id": 1434571,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852309913.157, "dur": 2.634, + "args": { + "External id": 1434572,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852309917.782, "dur": 46.089, + "args": { + "External id": 1434573,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852309923.371, "dur": 3.187, + "args": { + "External id": 1434574,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852309965.496, "dur": 1.933, + "args": { + "External id": 1434575,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852309966.590, "dur": 0.721, + "args": { + "External id": 1434576,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852309968.330, "dur": 38.459, + "args": { + "External id": 1434577,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852309972.758, "dur": 0.479, + "args": { + "External id": 1434578,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852310134.154, "dur": 30.248, + "args": { + "External id": 1434579,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852310183.643, "dur": 18.371, + "args": { + "External id": 1434580,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852310209.776, "dur": 50.906, + "args": { + "External id": 1434581,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852310267.135, "dur": 39.692, + "args": { + "External id": 1434582,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852310317.461, "dur": 38.990, + "args": { + "External id": 1434583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852310370.281, "dur": 36.722, + "args": { + "External id": 1434584,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852310414.519, "dur": 27.409, + "args": { + "External id": 1434585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852310451.211, "dur": 29.842, + "args": { + "External id": 1434586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852310503.594, "dur": 29.155, + "args": { + "External id": 1434587,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852310551.299, "dur": 25.459, + "args": { + "External id": 1434588,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852310597.392, "dur": 18.576, + "args": { + "External id": 1434589,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852310634.554, "dur": 19.961, + "args": { + "External id": 1434590,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852310669.850, "dur": 16.828, + "args": { + "External id": 1434591,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310767.596, "dur": 15.599, + "args": { + "External id": 1434592,"Record function id": 0, "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310771.184, "dur": 11.011, + "args": { + "External id": 1434593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310775.663, "dur": 5.456, + "args": { + "External id": 1434594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310777.059, "dur": 3.936, + "args": { + "External id": 1434595,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310787.195, "dur": 5.320, + "args": { + "External id": 1434596,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310789.004, "dur": 3.084, + "args": { + "External id": 1434597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310789.777, "dur": 1.682, + "args": { + "External id": 1434598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310790.411, "dur": 0.960, + "args": { + "External id": 1434599,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310796.049, "dur": 7.439, + "args": { + "External id": 1434600,"Record function id": 0, "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310797.535, "dur": 5.476, + "args": { + "External id": 1434601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310798.375, "dur": 4.225, + "args": { + "External id": 1434602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310799.043, "dur": 3.447, + "args": { + "External id": 1434603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310806.678, "dur": 4.444, + "args": { + "External id": 1434604,"Record function id": 0, "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310808.105, "dur": 2.605, + "args": { + "External id": 1434605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310808.977, "dur": 1.325, + "args": { + "External id": 1434606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310809.367, "dur": 0.863, + "args": { + "External id": 1434607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310814.223, "dur": 4.120, + "args": { + "External id": 1434608,"Record function id": 0, "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310815.808, "dur": 2.109, + "args": { + "External id": 1434609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310816.417, "dur": 1.109, + "args": { + "External id": 1434610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310816.817, "dur": 0.636, + "args": { + "External id": 1434611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310821.583, "dur": 4.820, + "args": { + "External id": 1434612,"Record function id": 0, "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310823.264, "dur": 2.689, + "args": { + "External id": 1434613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310824.148, "dur": 1.162, + "args": { + "External id": 1434614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310824.645, "dur": 0.591, + "args": { + "External id": 1434615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310829.640, "dur": 3.899, + "args": { + "External id": 1434616,"Record function id": 0, "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310831.117, "dur": 2.024, + "args": { + "External id": 1434617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310831.594, "dur": 1.118, + "args": { + "External id": 1434618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310831.980, "dur": 0.661, + "args": { + "External id": 1434619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310836.742, "dur": 6.121, + "args": { + "External id": 1434620,"Record function id": 0, "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310838.310, "dur": 4.108, + "args": { + "External id": 1434621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310838.999, "dur": 3.013, + "args": { + "External id": 1434622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310841.353, "dur": 0.592, + "args": { + "External id": 1434623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310846.123, "dur": 83.681, + "args": { + "External id": 1434624,"Record function id": 0, "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852310926.432, "dur": 2.829, + "args": { + "External id": 1434625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310927.461, "dur": 1.237, + "args": { + "External id": 1434626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852310927.831, "dur": 0.740, + "args": { + "External id": 1434627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852310934.840, "dur": 74908.296, + "args": { + "External id": 1434628,"Record function id": 0, "Sequence number": 15348673, "Fwd thread id": 1, "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852310936.652, "dur": 74897.822, + "args": { + "External id": 1434629,"Sequence number": 15348673, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4612 + } + }, + { + "ph": "f", "id": 209, "pid": 2338706, "tid": 2379422, "ts": 6413852310936.652, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413852310968.427, "dur": 59.502, + "args": { + "External id": 1434630,"Record function id": 0, "Ev Idx": 4613 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413852311037.223, "dur": 105.588, + "args": { + "External id": 1434631,"Record function id": 0, "Ev Idx": 4614 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413852311152.091, "dur": 74674.280, + "args": { + "External id": 1434632,"Record function id": 0, "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852311246.751, "dur": 8.322, + "args": { + "External id": 1434633,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852311266.192, "dur": 6.900, + "args": { + "External id": 1434634,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852311287.793, "dur": 73614.491, + "args": { + "External id": 1434635,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852311301.483, "dur": 73587.748, + "args": { + "External id": 1434636,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852311409.201, "dur": 18.906, + "args": { + "External id": 1434637,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852311450.310, "dur": 73391.952, + "args": { + "External id": 1434638,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852311453.080, "dur": 73387.999, + "args": { + "External id": 1434639,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852311458.120, "dur": 11.431, + "args": { + "External id": 1434640,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852311471.799, "dur": 73364.191, + "args": { + "External id": 1434641,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852385026.978, "dur": 12.999, + "args": { + "External id": 1434642,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852385030.639, "dur": 8.745, + "args": { + "External id": 1434643,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852385098.096, "dur": 427.954, + "args": { + "External id": 1434644,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852385132.948, "dur": 388.114, + "args": { + "External id": 1434645,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4628, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852385147.313, "dur": 367.759, + "args": { + "External id": 1434646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852385548.449, "dur": 2.421, + "args": { + "External id": 1434647,"Record function id": 0, "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": 4630, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385615.002, "dur": 7.368, + "args": { + "External id": 1434648,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385669.160, "dur": 1.430, + "args": { + "External id": 1434649,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385687.266, "dur": 3.838, + "args": { + "External id": 1434650,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385703.515, "dur": 0.794, + "args": { + "External id": 1434651,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385714.954, "dur": 0.862, + "args": { + "External id": 1434652,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385726.451, "dur": 0.759, + "args": { + "External id": 1434653,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385740.286, "dur": 2.844, + "args": { + "External id": 1434654,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385754.100, "dur": 2.322, + "args": { + "External id": 1434655,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852385766.231, "dur": 0.895, + "args": { + "External id": 1434656,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852385858.039, "dur": 3012.380, + "args": { + "External id": 1434657,"Record function id": 0, "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413852385877.743, "dur": 1126.679, + "args": { + "External id": 1434658,"Record function id": 0, "Ev Idx": 4641 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413852385891.398, "dur": 397.916, + "args": { + "External id": 1434659,"Record function id": 0, "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852385998.497, "dur": 4.622, + "args": { + "External id": 1434660,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386007.502, "dur": 0.817, + "args": { + "External id": 1434661,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386010.111, "dur": 3.417, + "args": { + "External id": 1434662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386015.386, "dur": 0.936, + "args": { + "External id": 1434663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386019.943, "dur": 1.091, + "args": { + "External id": 1434664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386022.544, "dur": 0.969, + "args": { + "External id": 1434665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386025.171, "dur": 2.069, + "args": { + "External id": 1434666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386028.879, "dur": 0.787, + "args": { + "External id": 1434667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386032.805, "dur": 0.707, + "args": { + "External id": 1434668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852386035.120, "dur": 0.471, + "args": { + "External id": 1434669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852386087.295, "dur": 169.558, + "args": { + "External id": 1434670,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852386106.345, "dur": 145.598, + "args": { + "External id": 1434671,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852386127.119, "dur": 18.470, + "args": { + "External id": 1434672,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852386149.681, "dur": 73.671, + "args": { + "External id": 1434673,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852386154.907, "dur": 68.182, + "args": { + "External id": 1434674,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386164.003, "dur": 6.470, + "args": { + "External id": 1434675,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852386172.449, "dur": 49.987, + "args": { + "External id": 1434676,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 2338706, "tid": 2379422, + "ts": 6413852386385.029, "dur": 589.646, + "args": { + "External id": 1434677,"Record function id": 0, "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413852386402.776, "dur": 559.780, + "args": { + "External id": 1434678,"Record function id": 0, "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852386467.373, "dur": 4.658, + "args": { + "External id": 1434679,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852386487.331, "dur": 37.649, + "args": { + "External id": 1434680,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386493.463, "dur": 3.047, + "args": { + "External id": 1434681,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386498.590, "dur": 0.360, + "args": { + "External id": 1434682,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386500.966, "dur": 0.301, + "args": { + "External id": 1434683,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386504.701, "dur": 0.517, + "args": { + "External id": 1434684,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386506.574, "dur": 0.549, + "args": { + "External id": 1434685,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386508.946, "dur": 2.680, + "args": { + "External id": 1434686,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386514.852, "dur": 0.368, + "args": { + "External id": 1434687,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386517.016, "dur": 0.435, + "args": { + "External id": 1434688,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386519.168, "dur": 1.128, + "args": { + "External id": 1434689,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852386536.525, "dur": 45.785, + "args": { + "External id": 1434690,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852386614.180, "dur": 114.355, + "args": { + "External id": 1434691,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852386623.571, "dur": 3.680, + "args": { + "External id": 1434692,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852386632.495, "dur": 10.707, + "args": { + "External id": 1434693,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852386636.720, "dur": 6.052, + "args": { + "External id": 1434694,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386640.630, "dur": 0.917, + "args": { + "External id": 1434695,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852386650.284, "dur": 28.086, + "args": { + "External id": 1434696,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386652.760, "dur": 0.577, + "args": { + "External id": 1434697,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386655.158, "dur": 0.394, + "args": { + "External id": 1434698,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386657.165, "dur": 2.947, + "args": { + "External id": 1434699,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386662.056, "dur": 0.289, + "args": { + "External id": 1434700,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386663.578, "dur": 0.436, + "args": { + "External id": 1434701,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386666.474, "dur": 0.376, + "args": { + "External id": 1434702,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386668.579, "dur": 0.506, + "args": { + "External id": 1434703,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386670.752, "dur": 0.328, + "args": { + "External id": 1434704,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852386673.659, "dur": 0.617, + "args": { + "External id": 1434705,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852386690.998, "dur": 30.561, + "args": { + "External id": 1434706,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852386772.640, "dur": 120.645, + "args": { + "External id": 1434707,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852386802.423, "dur": 87.694, + "args": { + "External id": 1434708,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4691, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852386811.946, "dur": 74.105, + "args": { + "External id": 1434709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852386912.672, "dur": 1.954, + "args": { + "External id": 1434710,"Record function id": 0, "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": 4693, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852387013.608, "dur": 1832.035, + "args": { + "External id": 1434711,"Sequence number": 15348672, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4694 + } + }, + { + "ph": "f", "id": 210, "pid": 2338706, "tid": 2379422, "ts": 6413852387013.608, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387169.942, "dur": 109.725, + "args": { + "External id": 1434712,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852387327.235, "dur": 42.449, + "args": { + "External id": 1434713,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387388.141, "dur": 48.791, + "args": { + "External id": 1434714,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387449.505, "dur": 32.210, + "args": { + "External id": 1434715,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387515.914, "dur": 34.274, + "args": { + "External id": 1434716,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387558.108, "dur": 28.772, + "args": { + "External id": 1434717,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387595.633, "dur": 28.114, + "args": { + "External id": 1434718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852387653.357, "dur": 23.723, + "args": { + "External id": 1434719,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852387711.457, "dur": 29.140, + "args": { + "External id": 1434720,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852387765.464, "dur": 20.860, + "args": { + "External id": 1434721,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852387799.790, "dur": 14.415, + "args": { + "External id": 1434722,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387823.042, "dur": 37.370, + "args": { + "External id": 1434723,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852387863.784, "dur": 32.465, + "args": { + "External id": 1434724,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852387927.039, "dur": 315.154, + "args": { + "External id": 1434725,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852388028.055, "dur": 7.033, + "args": { + "External id": 1434726,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852388037.621, "dur": 2.782, + "args": { + "External id": 1434727,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852388041.877, "dur": 4.397, + "args": { + "External id": 1434728,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852388047.555, "dur": 2.044, + "args": { + "External id": 1434729,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852388129.255, "dur": 8.387, + "args": { + "External id": 1434730,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852388134.188, "dur": 3.061, + "args": { + "External id": 1434731,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852388139.802, "dur": 34.810, + "args": { + "External id": 1434732,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852388146.018, "dur": 3.748, + "args": { + "External id": 1434733,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852388176.242, "dur": 1.779, + "args": { + "External id": 1434734,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852388177.298, "dur": 0.629, + "args": { + "External id": 1434735,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852388179.273, "dur": 16.539, + "args": { + "External id": 1434736,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852388183.165, "dur": 0.929, + "args": { + "External id": 1434737,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852388286.103, "dur": 27.463, + "args": { + "External id": 1434738,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852388333.298, "dur": 16.735, + "args": { + "External id": 1434739,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852388357.896, "dur": 47.505, + "args": { + "External id": 1434740,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852388411.686, "dur": 37.133, + "args": { + "External id": 1434741,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852388459.711, "dur": 35.678, + "args": { + "External id": 1434742,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852388510.942, "dur": 35.550, + "args": { + "External id": 1434743,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852388553.815, "dur": 28.553, + "args": { + "External id": 1434744,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852388590.600, "dur": 31.955, + "args": { + "External id": 1434745,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852388646.092, "dur": 27.090, + "args": { + "External id": 1434746,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852388692.161, "dur": 24.824, + "args": { + "External id": 1434747,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852388734.195, "dur": 17.875, + "args": { + "External id": 1434748,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852388770.943, "dur": 14.113, + "args": { + "External id": 1434749,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852388800.661, "dur": 14.929, + "args": { + "External id": 1434750,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388894.293, "dur": 14.590, + "args": { + "External id": 1434751,"Record function id": 0, "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388897.318, "dur": 10.625, + "args": { + "External id": 1434752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388901.518, "dur": 5.516, + "args": { + "External id": 1434753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388903.108, "dur": 3.838, + "args": { + "External id": 1434754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388912.652, "dur": 4.933, + "args": { + "External id": 1434755,"Record function id": 0, "Ev Idx": 4738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388914.327, "dur": 2.838, + "args": { + "External id": 1434756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388915.179, "dur": 1.390, + "args": { + "External id": 1434757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388915.647, "dur": 0.846, + "args": { + "External id": 1434758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388920.765, "dur": 7.167, + "args": { + "External id": 1434759,"Record function id": 0, "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388922.725, "dur": 4.773, + "args": { + "External id": 1434760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388923.340, "dur": 3.726, + "args": { + "External id": 1434761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388923.935, "dur": 3.024, + "args": { + "External id": 1434762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388931.221, "dur": 4.639, + "args": { + "External id": 1434763,"Record function id": 0, "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388932.556, "dur": 2.875, + "args": { + "External id": 1434764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388933.400, "dur": 1.362, + "args": { + "External id": 1434765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388933.704, "dur": 0.990, + "args": { + "External id": 1434766,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388938.908, "dur": 3.924, + "args": { + "External id": 1434767,"Record function id": 0, "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388940.249, "dur": 2.155, + "args": { + "External id": 1434768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388940.730, "dur": 1.240, + "args": { + "External id": 1434769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388941.170, "dur": 0.732, + "args": { + "External id": 1434770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388945.967, "dur": 4.249, + "args": { + "External id": 1434771,"Record function id": 0, "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388947.381, "dur": 2.431, + "args": { + "External id": 1434772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388948.079, "dur": 1.084, + "args": { + "External id": 1434773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388948.554, "dur": 0.545, + "args": { + "External id": 1434774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388953.740, "dur": 4.439, + "args": { + "External id": 1434775,"Record function id": 0, "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388955.149, "dur": 2.640, + "args": { + "External id": 1434776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388955.776, "dur": 1.463, + "args": { + "External id": 1434777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388956.336, "dur": 0.831, + "args": { + "External id": 1434778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388961.748, "dur": 6.123, + "args": { + "External id": 1434779,"Record function id": 0, "Ev Idx": 4762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388963.237, "dur": 4.223, + "args": { + "External id": 1434780,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388963.754, "dur": 3.183, + "args": { + "External id": 1434781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388966.272, "dur": 0.601, + "args": { + "External id": 1434782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388971.182, "dur": 21.595, + "args": { + "External id": 1434783,"Record function id": 0, "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852388972.162, "dur": 2.949, + "args": { + "External id": 1434784,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388973.272, "dur": 1.281, + "args": { + "External id": 1434785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852388973.832, "dur": 0.647, + "args": { + "External id": 1434786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852389000.269, "dur": 76158.876, + "args": { + "External id": 1434787,"Record function id": 0, "Sequence number": 15348671, "Fwd thread id": 1, "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852389002.814, "dur": 76146.463, + "args": { + "External id": 1434788,"Sequence number": 15348671, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4771 + } + }, + { + "ph": "f", "id": 211, "pid": 2338706, "tid": 2379422, "ts": 6413852389002.814, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413852389033.498, "dur": 75.045, + "args": { + "External id": 1434789,"Record function id": 0, "Ev Idx": 4772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413852389118.947, "dur": 72.625, + "args": { + "External id": 1434790,"Record function id": 0, "Ev Idx": 4773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413852389198.175, "dur": 75941.388, + "args": { + "External id": 1434791,"Record function id": 0, "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852389294.154, "dur": 7.717, + "args": { + "External id": 1434792,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852389312.524, "dur": 7.491, + "args": { + "External id": 1434793,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852389339.223, "dur": 74900.253, + "args": { + "External id": 1434794,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852389355.701, "dur": 74870.302, + "args": { + "External id": 1434795,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852389445.636, "dur": 17.854, + "args": { + "External id": 1434796,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852389482.970, "dur": 74694.890, + "args": { + "External id": 1434797,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852389485.993, "dur": 74690.598, + "args": { + "External id": 1434798,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852389491.221, "dur": 11.083, + "args": { + "External id": 1434799,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852389504.322, "dur": 74667.136, + "args": { + "External id": 1434800,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852464351.057, "dur": 12.865, + "args": { + "External id": 1434801,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852464354.780, "dur": 8.740, + "args": { + "External id": 1434802,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852464393.268, "dur": 383.305, + "args": { + "External id": 1434803,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852464428.151, "dur": 343.627, + "args": { + "External id": 1434804,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4787, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852464441.161, "dur": 324.673, + "args": { + "External id": 1434805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852464801.314, "dur": 2.477, + "args": { + "External id": 1434806,"Record function id": 0, "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": 4789, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852464862.180, "dur": 6.550, + "args": { + "External id": 1434807,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852464914.698, "dur": 1.979, + "args": { + "External id": 1434808,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852464932.250, "dur": 3.468, + "args": { + "External id": 1434809,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852464948.439, "dur": 0.843, + "args": { + "External id": 1434810,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852464961.562, "dur": 0.814, + "args": { + "External id": 1434811,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852464973.785, "dur": 0.970, + "args": { + "External id": 1434812,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465009.791, "dur": 3.596, + "args": { + "External id": 1434813,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465025.329, "dur": 2.398, + "args": { + "External id": 1434814,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465040.847, "dur": 1.078, + "args": { + "External id": 1434815,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852465177.694, "dur": 3028.740, + "args": { + "External id": 1434816,"Record function id": 0, "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413852465199.463, "dur": 1112.470, + "args": { + "External id": 1434817,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413852465216.409, "dur": 342.843, + "args": { + "External id": 1434818,"Record function id": 0, "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465313.767, "dur": 5.093, + "args": { + "External id": 1434819,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465322.272, "dur": 0.874, + "args": { + "External id": 1434820,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465325.039, "dur": 3.242, + "args": { + "External id": 1434821,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465330.311, "dur": 0.932, + "args": { + "External id": 1434822,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465332.804, "dur": 0.990, + "args": { + "External id": 1434823,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465335.381, "dur": 0.807, + "args": { + "External id": 1434824,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465340.251, "dur": 2.015, + "args": { + "External id": 1434825,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465344.059, "dur": 0.768, + "args": { + "External id": 1434826,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465346.432, "dur": 0.767, + "args": { + "External id": 1434827,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852465348.751, "dur": 0.679, + "args": { + "External id": 1434828,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852465373.202, "dur": 156.518, + "args": { + "External id": 1434829,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852465390.523, "dur": 134.659, + "args": { + "External id": 1434830,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852465410.187, "dur": 18.646, + "args": { + "External id": 1434831,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852465432.486, "dur": 63.834, + "args": { + "External id": 1434832,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852465435.010, "dur": 60.950, + "args": { + "External id": 1434833,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465439.083, "dur": 5.263, + "args": { + "External id": 1434834,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852465446.056, "dur": 49.336, + "args": { + "External id": 1434835,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4818 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 2338706, "tid": 2379422, + "ts": 6413852465650.829, "dur": 652.959, + "args": { + "External id": 1434836,"Record function id": 0, "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413852465668.469, "dur": 622.144, + "args": { + "External id": 1434837,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852465728.965, "dur": 4.961, + "args": { + "External id": 1434838,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852465749.649, "dur": 33.570, + "args": { + "External id": 1434839,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465755.079, "dur": 2.913, + "args": { + "External id": 1434840,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465759.876, "dur": 0.639, + "args": { + "External id": 1434841,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465762.193, "dur": 0.615, + "args": { + "External id": 1434842,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465765.860, "dur": 0.390, + "args": { + "External id": 1434843,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465767.849, "dur": 0.319, + "args": { + "External id": 1434844,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465769.342, "dur": 2.136, + "args": { + "External id": 1434845,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465773.538, "dur": 0.245, + "args": { + "External id": 1434846,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465775.459, "dur": 0.385, + "args": { + "External id": 1434847,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465777.567, "dur": 1.497, + "args": { + "External id": 1434848,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852465793.657, "dur": 42.451, + "args": { + "External id": 1434849,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852465866.383, "dur": 133.708, + "args": { + "External id": 1434850,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852465876.240, "dur": 3.798, + "args": { + "External id": 1434851,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852465885.037, "dur": 10.365, + "args": { + "External id": 1434852,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852465889.124, "dur": 5.857, + "args": { + "External id": 1434853,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465893.184, "dur": 0.534, + "args": { + "External id": 1434854,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852465901.496, "dur": 29.246, + "args": { + "External id": 1434855,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465904.419, "dur": 0.452, + "args": { + "External id": 1434856,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465906.619, "dur": 0.560, + "args": { + "External id": 1434857,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465908.751, "dur": 3.487, + "args": { + "External id": 1434858,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465914.038, "dur": 0.320, + "args": { + "External id": 1434859,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465915.975, "dur": 0.481, + "args": { + "External id": 1434860,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465919.132, "dur": 0.336, + "args": { + "External id": 1434861,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465921.062, "dur": 0.529, + "args": { + "External id": 1434862,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465923.148, "dur": 0.608, + "args": { + "External id": 1434863,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852465926.549, "dur": 0.506, + "args": { + "External id": 1434864,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852465943.208, "dur": 29.979, + "args": { + "External id": 1434865,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852466047.869, "dur": 165.046, + "args": { + "External id": 1434866,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852466114.345, "dur": 94.606, + "args": { + "External id": 1434867,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4850, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852466125.511, "dur": 79.095, + "args": { + "External id": 1434868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 4851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852466230.795, "dur": 2.259, + "args": { + "External id": 1434869,"Record function id": 0, "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": 4852, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852466320.112, "dur": 1865.251, + "args": { + "External id": 1434870,"Sequence number": 15348670, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4853 + } + }, + { + "ph": "f", "id": 212, "pid": 2338706, "tid": 2379422, "ts": 6413852466320.112, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852466435.980, "dur": 103.956, + "args": { + "External id": 1434871,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 4854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852466638.732, "dur": 42.167, + "args": { + "External id": 1434872,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 4855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852466700.092, "dur": 51.679, + "args": { + "External id": 1434873,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 4856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852466764.152, "dur": 32.287, + "args": { + "External id": 1434874,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852466802.584, "dur": 33.183, + "args": { + "External id": 1434875,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852466841.780, "dur": 26.996, + "args": { + "External id": 1434876,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852466883.202, "dur": 30.423, + "args": { + "External id": 1434877,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 4860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852466945.697, "dur": 26.026, + "args": { + "External id": 1434878,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 4861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852467014.638, "dur": 36.563, + "args": { + "External id": 1434879,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852467114.763, "dur": 22.871, + "args": { + "External id": 1434880,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852467153.663, "dur": 14.050, + "args": { + "External id": 1434881,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467176.005, "dur": 44.571, + "args": { + "External id": 1434882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467224.623, "dur": 32.122, + "args": { + "External id": 1434883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852467288.593, "dur": 247.888, + "args": { + "External id": 1434884,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852467369.201, "dur": 6.178, + "args": { + "External id": 1434885,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852467377.534, "dur": 3.216, + "args": { + "External id": 1434886,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852467382.125, "dur": 3.165, + "args": { + "External id": 1434887,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852467386.841, "dur": 3.544, + "args": { + "External id": 1434888,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852467432.241, "dur": 7.347, + "args": { + "External id": 1434889,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852467436.668, "dur": 2.762, + "args": { + "External id": 1434890,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852467441.672, "dur": 32.746, + "args": { + "External id": 1434891,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852467447.325, "dur": 3.838, + "args": { + "External id": 1434892,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852467475.740, "dur": 1.826, + "args": { + "External id": 1434893,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852467476.779, "dur": 0.691, + "args": { + "External id": 1434894,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852467478.648, "dur": 14.557, + "args": { + "External id": 1434895,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852467481.044, "dur": 0.661, + "args": { + "External id": 1434896,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 4879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852467576.814, "dur": 26.890, + "args": { + "External id": 1434897,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852467622.471, "dur": 16.336, + "args": { + "External id": 1434898,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467646.020, "dur": 36.355, + "args": { + "External id": 1434899,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467688.926, "dur": 36.501, + "args": { + "External id": 1434900,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467734.916, "dur": 19.505, + "args": { + "External id": 1434901,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 4884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467759.804, "dur": 30.357, + "args": { + "External id": 1434902,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 4885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467797.320, "dur": 27.171, + "args": { + "External id": 1434903,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 4886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852467839.442, "dur": 42.922, + "args": { + "External id": 1434904,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 4887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852467910.515, "dur": 23.698, + "args": { + "External id": 1434905,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 4888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852467953.136, "dur": 49.317, + "args": { + "External id": 1434906,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852468024.308, "dur": 20.949, + "args": { + "External id": 1434907,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 4890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852468102.905, "dur": 17.165, + "args": { + "External id": 1434908,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 4891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852468137.344, "dur": 16.693, + "args": { + "External id": 1434909,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 4892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468230.065, "dur": 15.777, + "args": { + "External id": 1434910,"Record function id": 0, "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468233.453, "dur": 11.385, + "args": { + "External id": 1434911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468238.009, "dur": 5.894, + "args": { + "External id": 1434912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468239.601, "dur": 4.213, + "args": { + "External id": 1434913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468249.738, "dur": 5.838, + "args": { + "External id": 1434914,"Record function id": 0, "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468251.763, "dur": 3.252, + "args": { + "External id": 1434915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468252.572, "dur": 1.659, + "args": { + "External id": 1434916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468253.316, "dur": 0.839, + "args": { + "External id": 1434917,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468259.133, "dur": 7.009, + "args": { + "External id": 1434918,"Record function id": 0, "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468260.388, "dur": 5.291, + "args": { + "External id": 1434919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468260.926, "dur": 4.302, + "args": { + "External id": 1434920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468261.726, "dur": 3.390, + "args": { + "External id": 1434921,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 4904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468269.504, "dur": 4.441, + "args": { + "External id": 1434922,"Record function id": 0, "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468271.063, "dur": 2.415, + "args": { + "External id": 1434923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468271.659, "dur": 1.404, + "args": { + "External id": 1434924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468272.260, "dur": 0.722, + "args": { + "External id": 1434925,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 4908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468277.206, "dur": 4.489, + "args": { + "External id": 1434926,"Record function id": 0, "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468278.610, "dur": 2.635, + "args": { + "External id": 1434927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468279.264, "dur": 1.555, + "args": { + "External id": 1434928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468279.742, "dur": 1.010, + "args": { + "External id": 1434929,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468284.904, "dur": 4.862, + "args": { + "External id": 1434930,"Record function id": 0, "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468286.627, "dur": 2.693, + "args": { + "External id": 1434931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468287.277, "dur": 1.351, + "args": { + "External id": 1434932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468287.735, "dur": 0.818, + "args": { + "External id": 1434933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 4916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468293.115, "dur": 4.262, + "args": { + "External id": 1434934,"Record function id": 0, "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468294.629, "dur": 2.334, + "args": { + "External id": 1434935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468295.340, "dur": 1.011, + "args": { + "External id": 1434936,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468295.652, "dur": 0.633, + "args": { + "External id": 1434937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468300.466, "dur": 5.670, + "args": { + "External id": 1434938,"Record function id": 0, "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468301.556, "dur": 4.142, + "args": { + "External id": 1434939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468302.025, "dur": 3.288, + "args": { + "External id": 1434940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468304.599, "dur": 0.611, + "args": { + "External id": 1434941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 4924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468309.292, "dur": 3.560, + "args": { + "External id": 1434942,"Record function id": 0, "Ev Idx": 4925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852468310.551, "dur": 1.895, + "args": { + "External id": 1434943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468311.034, "dur": 0.946, + "args": { + "External id": 1434944,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852468311.362, "dur": 0.536, + "args": { + "External id": 1434945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852468317.520, "dur": 72681.372, + "args": { + "External id": 1434946,"Record function id": 0, "Sequence number": 15348669, "Fwd thread id": 1, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852468319.395, "dur": 72651.011, + "args": { + "External id": 1434947,"Sequence number": 15348669, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 4930 + } + }, + { + "ph": "f", "id": 213, "pid": 2338706, "tid": 2379422, "ts": 6413852468319.395, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413852468348.504, "dur": 38.983, + "args": { + "External id": 1434948,"Record function id": 0, "Ev Idx": 4931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413852468395.390, "dur": 67.437, + "args": { + "External id": 1434949,"Record function id": 0, "Ev Idx": 4932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413852468471.310, "dur": 72490.385, + "args": { + "External id": 1434950,"Record function id": 0, "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852468563.275, "dur": 7.063, + "args": { + "External id": 1434951,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852468579.865, "dur": 6.390, + "args": { + "External id": 1434952,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852468602.437, "dur": 71528.217, + "args": { + "External id": 1434953,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852468617.237, "dur": 71499.613, + "args": { + "External id": 1434954,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 4937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852468706.047, "dur": 18.005, + "args": { + "External id": 1434955,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852468744.046, "dur": 71289.699, + "args": { + "External id": 1434956,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 4939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852468747.389, "dur": 71285.323, + "args": { + "External id": 1434957,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 4940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852468753.285, "dur": 9.317, + "args": { + "External id": 1434958,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852468766.923, "dur": 71260.446, + "args": { + "External id": 1434959,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 4942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852540242.809, "dur": 12.457, + "args": { + "External id": 1434960,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 4943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852540246.473, "dur": 8.391, + "args": { + "External id": 1434961,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852540286.832, "dur": 381.713, + "args": { + "External id": 1434962,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852540321.213, "dur": 342.416, + "args": { + "External id": 1434963,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4946, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852540334.902, "dur": 322.902, + "args": { + "External id": 1434964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 4947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852540691.259, "dur": 2.138, + "args": { + "External id": 1434965,"Record function id": 0, "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": 4948, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540751.613, "dur": 6.885, + "args": { + "External id": 1434966,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540803.244, "dur": 1.457, + "args": { + "External id": 1434967,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540821.062, "dur": 3.330, + "args": { + "External id": 1434968,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540836.681, "dur": 0.830, + "args": { + "External id": 1434969,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540848.685, "dur": 0.831, + "args": { + "External id": 1434970,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540861.078, "dur": 0.668, + "args": { + "External id": 1434971,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540875.855, "dur": 2.992, + "args": { + "External id": 1434972,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540889.869, "dur": 2.103, + "args": { + "External id": 1434973,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852540902.128, "dur": 0.741, + "args": { + "External id": 1434974,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852541017.033, "dur": 2999.781, + "args": { + "External id": 1434975,"Record function id": 0, "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413852541039.688, "dur": 1165.493, + "args": { + "External id": 1434976,"Record function id": 0, "Ev Idx": 4959 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413852541089.052, "dur": 350.373, + "args": { + "External id": 1434977,"Record function id": 0, "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541187.494, "dur": 5.525, + "args": { + "External id": 1434978,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541196.579, "dur": 0.829, + "args": { + "External id": 1434979,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541199.408, "dur": 3.167, + "args": { + "External id": 1434980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541206.615, "dur": 0.794, + "args": { + "External id": 1434981,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541208.987, "dur": 0.888, + "args": { + "External id": 1434982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541211.661, "dur": 0.874, + "args": { + "External id": 1434983,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 4966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541214.161, "dur": 2.066, + "args": { + "External id": 1434984,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 4967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541219.485, "dur": 0.646, + "args": { + "External id": 1434985,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541221.959, "dur": 0.716, + "args": { + "External id": 1434986,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852541224.368, "dur": 0.679, + "args": { + "External id": 1434987,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 4970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852541244.984, "dur": 161.527, + "args": { + "External id": 1434988,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852541261.947, "dur": 140.416, + "args": { + "External id": 1434989,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 4972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852541283.860, "dur": 19.617, + "args": { + "External id": 1434990,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852541309.391, "dur": 65.455, + "args": { + "External id": 1434991,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 4974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852541312.254, "dur": 62.294, + "args": { + "External id": 1434992,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 4975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541316.351, "dur": 6.351, + "args": { + "External id": 1434993,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852541324.536, "dur": 49.404, + "args": { + "External id": 1434994,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 2338706, "tid": 2379422, + "ts": 6413852541534.607, "dur": 662.675, + "args": { + "External id": 1434995,"Record function id": 0, "Ev Idx": 4978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413852541550.898, "dur": 633.819, + "args": { + "External id": 1434996,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852541613.332, "dur": 4.514, + "args": { + "External id": 1434997,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852541634.361, "dur": 33.619, + "args": { + "External id": 1434998,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541639.370, "dur": 3.424, + "args": { + "External id": 1434999,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541644.590, "dur": 0.495, + "args": { + "External id": 1435000,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541646.491, "dur": 0.634, + "args": { + "External id": 1435001,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541649.690, "dur": 0.302, + "args": { + "External id": 1435002,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541651.333, "dur": 0.361, + "args": { + "External id": 1435003,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541653.221, "dur": 2.086, + "args": { + "External id": 1435004,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541658.201, "dur": 0.304, + "args": { + "External id": 1435005,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541659.862, "dur": 0.385, + "args": { + "External id": 1435006,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541661.756, "dur": 1.419, + "args": { + "External id": 1435007,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852541678.872, "dur": 40.274, + "args": { + "External id": 1435008,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 4991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852541749.750, "dur": 112.261, + "args": { + "External id": 1435009,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 4992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852541759.742, "dur": 3.907, + "args": { + "External id": 1435010,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852541768.894, "dur": 10.186, + "args": { + "External id": 1435011,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852541773.113, "dur": 5.560, + "args": { + "External id": 1435012,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 4995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541776.977, "dur": 0.543, + "args": { + "External id": 1435013,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 4996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852541785.734, "dur": 26.664, + "args": { + "External id": 1435014,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 4997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541788.169, "dur": 0.649, + "args": { + "External id": 1435015,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541790.519, "dur": 0.441, + "args": { + "External id": 1435016,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 4999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541792.346, "dur": 3.727, + "args": { + "External id": 1435017,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541797.553, "dur": 0.403, + "args": { + "External id": 1435018,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541799.342, "dur": 0.412, + "args": { + "External id": 1435019,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541802.642, "dur": 0.371, + "args": { + "External id": 1435020,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541804.234, "dur": 0.341, + "args": { + "External id": 1435021,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541805.972, "dur": 0.383, + "args": { + "External id": 1435022,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852541808.410, "dur": 0.326, + "args": { + "External id": 1435023,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852541824.322, "dur": 29.852, + "args": { + "External id": 1435024,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852541905.734, "dur": 192.258, + "args": { + "External id": 1435025,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852541936.768, "dur": 156.994, + "args": { + "External id": 1435026,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5009, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852541945.730, "dur": 140.906, + "args": { + "External id": 1435027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852542121.735, "dur": 2.421, + "args": { + "External id": 1435028,"Record function id": 0, "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": 5011, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852542213.244, "dur": 1756.413, + "args": { + "External id": 1435029,"Sequence number": 15348668, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5012 + } + }, + { + "ph": "f", "id": 214, "pid": 2338706, "tid": 2379422, "ts": 6413852542213.244, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542330.555, "dur": 109.040, + "args": { + "External id": 1435030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852542487.428, "dur": 46.807, + "args": { + "External id": 1435031,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542552.722, "dur": 50.313, + "args": { + "External id": 1435032,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542616.333, "dur": 31.507, + "args": { + "External id": 1435033,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542654.115, "dur": 32.134, + "args": { + "External id": 1435034,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542692.008, "dur": 26.299, + "args": { + "External id": 1435035,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542725.709, "dur": 27.763, + "args": { + "External id": 1435036,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852542779.999, "dur": 24.023, + "args": { + "External id": 1435037,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852542847.289, "dur": 29.254, + "args": { + "External id": 1435038,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852542902.217, "dur": 18.903, + "args": { + "External id": 1435039,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852542936.089, "dur": 13.615, + "args": { + "External id": 1435040,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852542957.205, "dur": 55.648, + "args": { + "External id": 1435041,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543018.360, "dur": 68.998, + "args": { + "External id": 1435042,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852543125.903, "dur": 258.962, + "args": { + "External id": 1435043,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852543205.102, "dur": 6.765, + "args": { + "External id": 1435044,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852543214.053, "dur": 2.683, + "args": { + "External id": 1435045,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852543218.449, "dur": 3.311, + "args": { + "External id": 1435046,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852543223.026, "dur": 2.183, + "args": { + "External id": 1435047,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852543272.639, "dur": 5.023, + "args": { + "External id": 1435048,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852543274.801, "dur": 2.679, + "args": { + "External id": 1435049,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852543282.242, "dur": 36.163, + "args": { + "External id": 1435050,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852543289.210, "dur": 3.712, + "args": { + "External id": 1435051,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852543319.929, "dur": 1.838, + "args": { + "External id": 1435052,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852543321.074, "dur": 0.607, + "args": { + "External id": 1435053,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852543322.831, "dur": 18.933, + "args": { + "External id": 1435054,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852543326.773, "dur": 0.454, + "args": { + "External id": 1435055,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852543427.279, "dur": 27.989, + "args": { + "External id": 1435056,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852543474.963, "dur": 16.758, + "args": { + "External id": 1435057,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543499.481, "dur": 44.055, + "args": { + "External id": 1435058,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543549.973, "dur": 37.483, + "args": { + "External id": 1435059,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543597.999, "dur": 20.775, + "args": { + "External id": 1435060,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543623.939, "dur": 30.086, + "args": { + "External id": 1435061,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543661.128, "dur": 26.535, + "args": { + "External id": 1435062,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852543693.697, "dur": 29.156, + "args": { + "External id": 1435063,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852543743.574, "dur": 23.940, + "args": { + "External id": 1435064,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852543786.539, "dur": 44.106, + "args": { + "External id": 1435065,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852543856.576, "dur": 19.812, + "args": { + "External id": 1435066,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852543894.222, "dur": 14.970, + "args": { + "External id": 1435067,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852543923.484, "dur": 17.853, + "args": { + "External id": 1435068,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544040.558, "dur": 53.656, + "args": { + "External id": 1435069,"Record function id": 0, "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544044.206, "dur": 48.389, + "args": { + "External id": 1435070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544048.381, "dur": 42.458, + "args": { + "External id": 1435071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544049.829, "dur": 40.485, + "args": { + "External id": 1435072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544101.112, "dur": 6.635, + "args": { + "External id": 1435073,"Record function id": 0, "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544103.312, "dur": 3.958, + "args": { + "External id": 1435074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544104.897, "dur": 1.751, + "args": { + "External id": 1435075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544105.512, "dur": 1.049, + "args": { + "External id": 1435076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544111.153, "dur": 7.506, + "args": { + "External id": 1435077,"Record function id": 0, "Ev Idx": 5060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544112.733, "dur": 5.435, + "args": { + "External id": 1435078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544113.261, "dur": 4.225, + "args": { + "External id": 1435079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544113.701, "dur": 3.717, + "args": { + "External id": 1435080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544121.867, "dur": 4.068, + "args": { + "External id": 1435081,"Record function id": 0, "Ev Idx": 5064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544123.183, "dur": 2.336, + "args": { + "External id": 1435082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544123.653, "dur": 1.312, + "args": { + "External id": 1435083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544124.146, "dur": 0.731, + "args": { + "External id": 1435084,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544128.987, "dur": 6.273, + "args": { + "External id": 1435085,"Record function id": 0, "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544130.503, "dur": 4.302, + "args": { + "External id": 1435086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544131.048, "dur": 3.126, + "args": { + "External id": 1435087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544133.418, "dur": 0.648, + "args": { + "External id": 1435088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544138.560, "dur": 4.086, + "args": { + "External id": 1435089,"Record function id": 0, "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544139.950, "dur": 2.271, + "args": { + "External id": 1435090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544140.456, "dur": 1.292, + "args": { + "External id": 1435091,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544140.943, "dur": 0.711, + "args": { + "External id": 1435092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544146.023, "dur": 4.039, + "args": { + "External id": 1435093,"Record function id": 0, "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544147.390, "dur": 2.238, + "args": { + "External id": 1435094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544148.117, "dur": 1.066, + "args": { + "External id": 1435095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544148.489, "dur": 0.621, + "args": { + "External id": 1435096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544153.281, "dur": 4.407, + "args": { + "External id": 1435097,"Record function id": 0, "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544154.715, "dur": 2.346, + "args": { + "External id": 1435098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544155.430, "dur": 1.221, + "args": { + "External id": 1435099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544155.908, "dur": 0.669, + "args": { + "External id": 1435100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544161.074, "dur": 7.007, + "args": { + "External id": 1435101,"Record function id": 0, "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852544162.153, "dur": 5.488, + "args": { + "External id": 1435102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544163.017, "dur": 4.064, + "args": { + "External id": 1435103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852544166.099, "dur": 0.883, + "args": { + "External id": 1435104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852544172.858, "dur": 67566.602, + "args": { + "External id": 1435105,"Record function id": 0, "Sequence number": 15348667, "Fwd thread id": 1, "Ev Idx": 5088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852544174.966, "dur": 67555.892, + "args": { + "External id": 1435106,"Sequence number": 15348667, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5089 + } + }, + { + "ph": "f", "id": 215, "pid": 2338706, "tid": 2379422, "ts": 6413852544174.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413852544206.751, "dur": 39.816, + "args": { + "External id": 1435107,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413852544254.596, "dur": 66.592, + "args": { + "External id": 1435108,"Record function id": 0, "Ev Idx": 5091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413852544327.253, "dur": 67394.816, + "args": { + "External id": 1435109,"Record function id": 0, "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852544418.820, "dur": 7.664, + "args": { + "External id": 1435110,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852544435.850, "dur": 6.947, + "args": { + "External id": 1435111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852544458.259, "dur": 66324.709, + "args": { + "External id": 1435112,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852544473.339, "dur": 66295.739, + "args": { + "External id": 1435113,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852544564.231, "dur": 18.200, + "args": { + "External id": 1435114,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852544602.094, "dur": 66119.382, + "args": { + "External id": 1435115,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852544604.988, "dur": 66115.375, + "args": { + "External id": 1435116,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852544609.591, "dur": 11.789, + "args": { + "External id": 1435117,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852544623.513, "dur": 66091.214, + "args": { + "External id": 1435118,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852610892.082, "dur": 12.637, + "args": { + "External id": 1435119,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852610895.870, "dur": 8.448, + "args": { + "External id": 1435120,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852610936.075, "dur": 476.938, + "args": { + "External id": 1435121,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852610970.647, "dur": 436.337, + "args": { + "External id": 1435122,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5105, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852611000.726, "dur": 400.405, + "args": { + "External id": 1435123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852611439.764, "dur": 2.356, + "args": { + "External id": 1435124,"Record function id": 0, "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": 5107, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611509.217, "dur": 6.853, + "args": { + "External id": 1435125,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611562.820, "dur": 1.323, + "args": { + "External id": 1435126,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611579.600, "dur": 4.213, + "args": { + "External id": 1435127,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611596.120, "dur": 1.171, + "args": { + "External id": 1435128,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611611.943, "dur": 0.977, + "args": { + "External id": 1435129,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611623.728, "dur": 0.892, + "args": { + "External id": 1435130,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611634.901, "dur": 3.130, + "args": { + "External id": 1435131,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611648.543, "dur": 2.214, + "args": { + "External id": 1435132,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852611660.290, "dur": 0.877, + "args": { + "External id": 1435133,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852611754.734, "dur": 3085.325, + "args": { + "External id": 1435134,"Record function id": 0, "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413852611777.328, "dur": 1196.802, + "args": { + "External id": 1435135,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413852611793.557, "dur": 488.104, + "args": { + "External id": 1435136,"Record function id": 0, "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852611966.556, "dur": 4.826, + "args": { + "External id": 1435137,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852611992.889, "dur": 2.008, + "args": { + "External id": 1435138,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852611998.910, "dur": 2.855, + "args": { + "External id": 1435139,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612005.813, "dur": 1.081, + "args": { + "External id": 1435140,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612008.372, "dur": 0.678, + "args": { + "External id": 1435141,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612010.662, "dur": 0.725, + "args": { + "External id": 1435142,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612013.069, "dur": 1.823, + "args": { + "External id": 1435143,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612018.750, "dur": 0.648, + "args": { + "External id": 1435144,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612022.189, "dur": 0.689, + "args": { + "External id": 1435145,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852612024.417, "dur": 0.474, + "args": { + "External id": 1435146,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852612046.306, "dur": 198.915, + "args": { + "External id": 1435147,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852612097.000, "dur": 142.741, + "args": { + "External id": 1435148,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852612118.259, "dur": 18.443, + "args": { + "External id": 1435149,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852612140.675, "dur": 69.079, + "args": { + "External id": 1435150,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852612143.398, "dur": 65.983, + "args": { + "External id": 1435151,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612147.277, "dur": 7.151, + "args": { + "External id": 1435152,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852612156.034, "dur": 52.731, + "args": { + "External id": 1435153,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 2338706, "tid": 2379422, + "ts": 6413852612380.008, "dur": 587.009, + "args": { + "External id": 1435154,"Record function id": 0, "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413852612399.242, "dur": 555.833, + "args": { + "External id": 1435155,"Record function id": 0, "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852612463.928, "dur": 4.971, + "args": { + "External id": 1435156,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852612484.549, "dur": 34.614, + "args": { + "External id": 1435157,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612490.163, "dur": 1.920, + "args": { + "External id": 1435158,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612494.405, "dur": 1.773, + "args": { + "External id": 1435159,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612497.796, "dur": 0.314, + "args": { + "External id": 1435160,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612500.021, "dur": 0.391, + "args": { + "External id": 1435161,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612503.471, "dur": 0.346, + "args": { + "External id": 1435162,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612505.481, "dur": 2.377, + "args": { + "External id": 1435163,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612509.199, "dur": 0.520, + "args": { + "External id": 1435164,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612512.202, "dur": 0.286, + "args": { + "External id": 1435165,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612514.161, "dur": 0.251, + "args": { + "External id": 1435166,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852612529.611, "dur": 42.729, + "args": { + "External id": 1435167,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852612603.502, "dur": 115.707, + "args": { + "External id": 1435168,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 5151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852612613.663, "dur": 3.438, + "args": { + "External id": 1435169,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852612622.197, "dur": 10.230, + "args": { + "External id": 1435170,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852612626.623, "dur": 5.371, + "args": { + "External id": 1435171,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 5154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612630.362, "dur": 0.599, + "args": { + "External id": 1435172,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852612639.109, "dur": 27.049, + "args": { + "External id": 1435173,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612641.438, "dur": 0.723, + "args": { + "External id": 1435174,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612645.021, "dur": 0.297, + "args": { + "External id": 1435175,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612646.626, "dur": 2.532, + "args": { + "External id": 1435176,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612650.728, "dur": 1.417, + "args": { + "External id": 1435177,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612653.493, "dur": 0.418, + "args": { + "External id": 1435178,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612655.563, "dur": 0.326, + "args": { + "External id": 1435179,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612658.388, "dur": 0.349, + "args": { + "External id": 1435180,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612660.216, "dur": 0.651, + "args": { + "External id": 1435181,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852612662.048, "dur": 0.619, + "args": { + "External id": 1435182,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852612680.622, "dur": 30.951, + "args": { + "External id": 1435183,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852612762.722, "dur": 123.530, + "args": { + "External id": 1435184,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852612796.550, "dur": 86.310, + "args": { + "External id": 1435185,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5168, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852612807.060, "dur": 71.884, + "args": { + "External id": 1435186,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852612906.467, "dur": 2.009, + "args": { + "External id": 1435187,"Record function id": 0, "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": 5170, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852613000.548, "dur": 1817.929, + "args": { + "External id": 1435188,"Sequence number": 15348666, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5171 + } + }, + { + "ph": "f", "id": 216, "pid": 2338706, "tid": 2379422, "ts": 6413852613000.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613158.869, "dur": 111.634, + "args": { + "External id": 1435189,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852613318.166, "dur": 44.810, + "args": { + "External id": 1435190,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613381.243, "dur": 50.235, + "args": { + "External id": 1435191,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613444.026, "dur": 32.022, + "args": { + "External id": 1435192,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613482.590, "dur": 33.344, + "args": { + "External id": 1435193,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613521.706, "dur": 26.803, + "args": { + "External id": 1435194,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613556.164, "dur": 29.384, + "args": { + "External id": 1435195,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852613613.595, "dur": 26.977, + "args": { + "External id": 1435196,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852613659.748, "dur": 30.261, + "args": { + "External id": 1435197,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852613717.523, "dur": 19.858, + "args": { + "External id": 1435198,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852613751.084, "dur": 15.239, + "args": { + "External id": 1435199,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613794.285, "dur": 36.337, + "args": { + "External id": 1435200,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852613834.602, "dur": 31.682, + "args": { + "External id": 1435201,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852613897.606, "dur": 309.139, + "args": { + "External id": 1435202,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852613992.823, "dur": 7.740, + "args": { + "External id": 1435203,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852614004.093, "dur": 2.674, + "args": { + "External id": 1435204,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852614008.355, "dur": 3.570, + "args": { + "External id": 1435205,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852614013.214, "dur": 2.847, + "args": { + "External id": 1435206,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852614092.676, "dur": 6.042, + "args": { + "External id": 1435207,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852614095.097, "dur": 3.261, + "args": { + "External id": 1435208,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852614100.702, "dur": 35.731, + "args": { + "External id": 1435209,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852614106.564, "dur": 4.990, + "args": { + "External id": 1435210,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852614138.064, "dur": 3.599, + "args": { + "External id": 1435211,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852614140.833, "dur": 0.691, + "args": { + "External id": 1435212,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852614142.660, "dur": 16.151, + "args": { + "External id": 1435213,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852614146.784, "dur": 0.682, + "args": { + "External id": 1435214,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852614252.831, "dur": 28.637, + "args": { + "External id": 1435215,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852614300.466, "dur": 17.632, + "args": { + "External id": 1435216,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852614325.845, "dur": 64.313, + "args": { + "External id": 1435217,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852614403.140, "dur": 44.387, + "args": { + "External id": 1435218,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852614458.889, "dur": 21.981, + "args": { + "External id": 1435219,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852614486.247, "dur": 33.080, + "args": { + "External id": 1435220,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852614526.213, "dur": 26.367, + "args": { + "External id": 1435221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852614562.275, "dur": 29.525, + "args": { + "External id": 1435222,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852614614.075, "dur": 27.057, + "args": { + "External id": 1435223,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852614660.975, "dur": 26.026, + "args": { + "External id": 1435224,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852614705.340, "dur": 19.217, + "args": { + "External id": 1435225,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852614741.602, "dur": 15.403, + "args": { + "External id": 1435226,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852614772.323, "dur": 17.267, + "args": { + "External id": 1435227,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614863.677, "dur": 14.630, + "args": { + "External id": 1435228,"Record function id": 0, "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614867.035, "dur": 10.306, + "args": { + "External id": 1435229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614871.185, "dur": 5.399, + "args": { + "External id": 1435230,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614872.699, "dur": 3.792, + "args": { + "External id": 1435231,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614882.172, "dur": 4.967, + "args": { + "External id": 1435232,"Record function id": 0, "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614884.040, "dur": 2.613, + "args": { + "External id": 1435233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614884.609, "dur": 1.264, + "args": { + "External id": 1435234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614884.937, "dur": 0.855, + "args": { + "External id": 1435235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614890.667, "dur": 6.327, + "args": { + "External id": 1435236,"Record function id": 0, "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614891.932, "dur": 4.625, + "args": { + "External id": 1435237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614892.396, "dur": 3.736, + "args": { + "External id": 1435238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614893.021, "dur": 3.039, + "args": { + "External id": 1435239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614900.295, "dur": 3.826, + "args": { + "External id": 1435240,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614901.682, "dur": 2.004, + "args": { + "External id": 1435241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614902.159, "dur": 1.124, + "args": { + "External id": 1435242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614902.457, "dur": 0.751, + "args": { + "External id": 1435243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614907.240, "dur": 6.268, + "args": { + "External id": 1435244,"Record function id": 0, "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614908.704, "dur": 4.371, + "args": { + "External id": 1435245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614909.140, "dur": 3.484, + "args": { + "External id": 1435246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614911.860, "dur": 0.648, + "args": { + "External id": 1435247,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614916.609, "dur": 3.992, + "args": { + "External id": 1435248,"Record function id": 0, "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614917.835, "dur": 2.372, + "args": { + "External id": 1435249,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614918.544, "dur": 1.074, + "args": { + "External id": 1435250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614918.959, "dur": 0.567, + "args": { + "External id": 1435251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614923.746, "dur": 3.617, + "args": { + "External id": 1435252,"Record function id": 0, "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614924.893, "dur": 2.068, + "args": { + "External id": 1435253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614925.340, "dur": 1.019, + "args": { + "External id": 1435254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614925.703, "dur": 0.578, + "args": { + "External id": 1435255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614930.434, "dur": 3.698, + "args": { + "External id": 1435256,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614931.750, "dur": 1.977, + "args": { + "External id": 1435257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614932.218, "dur": 1.092, + "args": { + "External id": 1435258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614932.568, "dur": 0.668, + "args": { + "External id": 1435259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614937.979, "dur": 5.621, + "args": { + "External id": 1435260,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852614939.129, "dur": 4.039, + "args": { + "External id": 1435261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614939.615, "dur": 2.986, + "args": { + "External id": 1435262,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852614941.818, "dur": 0.682, + "args": { + "External id": 1435263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852614948.052, "dur": 61836.944, + "args": { + "External id": 1435264,"Record function id": 0, "Sequence number": 15348665, "Fwd thread id": 1, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852614949.908, "dur": 61824.910, + "args": { + "External id": 1435265,"Sequence number": 15348665, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5248 + } + }, + { + "ph": "f", "id": 217, "pid": 2338706, "tid": 2379422, "ts": 6413852614949.908, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413852614997.246, "dur": 42.753, + "args": { + "External id": 1435266,"Record function id": 0, "Ev Idx": 5249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413852615048.857, "dur": 104.777, + "args": { + "External id": 1435267,"Record function id": 0, "Ev Idx": 5250 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413852615162.654, "dur": 61603.404, + "args": { + "External id": 1435268,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852615260.837, "dur": 7.956, + "args": { + "External id": 1435269,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852615283.226, "dur": 7.240, + "args": { + "External id": 1435270,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852615307.060, "dur": 60567.402, + "args": { + "External id": 1435271,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852615321.278, "dur": 60539.841, + "args": { + "External id": 1435272,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852615437.849, "dur": 18.459, + "args": { + "External id": 1435273,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852615476.246, "dur": 60334.740, + "args": { + "External id": 1435274,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852615479.131, "dur": 60330.699, + "args": { + "External id": 1435275,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852615483.451, "dur": 11.340, + "args": { + "External id": 1435276,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852615497.239, "dur": 60307.456, + "args": { + "External id": 1435277,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852675996.196, "dur": 13.185, + "args": { + "External id": 1435278,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852675999.861, "dur": 8.855, + "args": { + "External id": 1435279,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852676041.911, "dur": 419.633, + "args": { + "External id": 1435280,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852676104.890, "dur": 351.029, + "args": { + "External id": 1435281,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5264, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852676120.012, "dur": 330.234, + "args": { + "External id": 1435282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852676487.633, "dur": 2.394, + "args": { + "External id": 1435283,"Record function id": 0, "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": 5266, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676554.360, "dur": 6.737, + "args": { + "External id": 1435284,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676606.711, "dur": 1.269, + "args": { + "External id": 1435285,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676624.103, "dur": 3.275, + "args": { + "External id": 1435286,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676639.688, "dur": 0.763, + "args": { + "External id": 1435287,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676652.655, "dur": 0.823, + "args": { + "External id": 1435288,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676663.614, "dur": 0.714, + "args": { + "External id": 1435289,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676674.988, "dur": 3.023, + "args": { + "External id": 1435290,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676691.144, "dur": 2.220, + "args": { + "External id": 1435291,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852676703.263, "dur": 0.698, + "args": { + "External id": 1435292,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852676799.363, "dur": 3086.318, + "args": { + "External id": 1435293,"Record function id": 0, "Ev Idx": 5276 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413852676819.954, "dur": 1154.380, + "args": { + "External id": 1435294,"Record function id": 0, "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413852676836.295, "dur": 407.311, + "args": { + "External id": 1435295,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676932.641, "dur": 4.299, + "args": { + "External id": 1435296,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676940.313, "dur": 0.856, + "args": { + "External id": 1435297,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676943.037, "dur": 2.791, + "args": { + "External id": 1435298,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676947.641, "dur": 0.813, + "args": { + "External id": 1435299,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676950.091, "dur": 0.853, + "args": { + "External id": 1435300,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676954.649, "dur": 0.654, + "args": { + "External id": 1435301,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676956.901, "dur": 1.754, + "args": { + "External id": 1435302,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676960.234, "dur": 0.719, + "args": { + "External id": 1435303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676962.581, "dur": 0.876, + "args": { + "External id": 1435304,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852676967.157, "dur": 0.689, + "args": { + "External id": 1435305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852677007.115, "dur": 199.377, + "args": { + "External id": 1435306,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852677024.561, "dur": 176.443, + "args": { + "External id": 1435307,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852677044.918, "dur": 51.135, + "args": { + "External id": 1435308,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852677101.029, "dur": 67.840, + "args": { + "External id": 1435309,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852677103.617, "dur": 64.978, + "args": { + "External id": 1435310,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677107.853, "dur": 6.338, + "args": { + "External id": 1435311,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852677115.864, "dur": 52.073, + "args": { + "External id": 1435312,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 2338706, "tid": 2379422, + "ts": 6413852677346.314, "dur": 619.914, + "args": { + "External id": 1435313,"Record function id": 0, "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413852677365.343, "dur": 588.475, + "args": { + "External id": 1435314,"Record function id": 0, "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852677430.551, "dur": 5.313, + "args": { + "External id": 1435315,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852677452.074, "dur": 57.834, + "args": { + "External id": 1435316,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677457.244, "dur": 2.931, + "args": { + "External id": 1435317,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677484.003, "dur": 0.469, + "args": { + "External id": 1435318,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677486.732, "dur": 0.552, + "args": { + "External id": 1435319,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677490.532, "dur": 0.330, + "args": { + "External id": 1435320,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677492.163, "dur": 0.306, + "args": { + "External id": 1435321,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677493.881, "dur": 3.394, + "args": { + "External id": 1435322,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677499.005, "dur": 0.483, + "args": { + "External id": 1435323,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677500.863, "dur": 0.518, + "args": { + "External id": 1435324,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677504.410, "dur": 0.378, + "args": { + "External id": 1435325,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852677522.002, "dur": 46.416, + "args": { + "External id": 1435326,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852677600.606, "dur": 113.844, + "args": { + "External id": 1435327,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 5310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852677611.307, "dur": 3.578, + "args": { + "External id": 1435328,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852677619.989, "dur": 10.591, + "args": { + "External id": 1435329,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852677624.417, "dur": 5.720, + "args": { + "External id": 1435330,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 5313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677628.287, "dur": 0.645, + "args": { + "External id": 1435331,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852677637.490, "dur": 28.094, + "args": { + "External id": 1435332,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677640.472, "dur": 0.571, + "args": { + "External id": 1435333,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677642.743, "dur": 0.473, + "args": { + "External id": 1435334,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677646.308, "dur": 2.279, + "args": { + "External id": 1435335,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677649.943, "dur": 0.493, + "args": { + "External id": 1435336,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677652.041, "dur": 0.310, + "args": { + "External id": 1435337,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677654.508, "dur": 0.421, + "args": { + "External id": 1435338,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677656.205, "dur": 0.340, + "args": { + "External id": 1435339,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677658.250, "dur": 1.818, + "args": { + "External id": 1435340,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852677661.441, "dur": 0.422, + "args": { + "External id": 1435341,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852677677.433, "dur": 29.357, + "args": { + "External id": 1435342,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852677758.588, "dur": 123.030, + "args": { + "External id": 1435343,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852677792.263, "dur": 85.839, + "args": { + "External id": 1435344,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5327, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852677801.497, "dur": 72.155, + "args": { + "External id": 1435345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852677901.645, "dur": 1.652, + "args": { + "External id": 1435346,"Record function id": 0, "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": 5329, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852678002.626, "dur": 1861.465, + "args": { + "External id": 1435347,"Sequence number": 15348664, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5330 + } + }, + { + "ph": "f", "id": 218, "pid": 2338706, "tid": 2379422, "ts": 6413852678002.626, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678156.574, "dur": 110.310, + "args": { + "External id": 1435348,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852678315.382, "dur": 44.157, + "args": { + "External id": 1435349,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678378.053, "dur": 51.017, + "args": { + "External id": 1435350,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678441.523, "dur": 31.375, + "args": { + "External id": 1435351,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678479.066, "dur": 39.722, + "args": { + "External id": 1435352,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678524.864, "dur": 27.312, + "args": { + "External id": 1435353,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678560.498, "dur": 29.024, + "args": { + "External id": 1435354,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852678617.134, "dur": 27.081, + "args": { + "External id": 1435355,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852678663.577, "dur": 30.558, + "args": { + "External id": 1435356,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852678721.228, "dur": 20.403, + "args": { + "External id": 1435357,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852678755.006, "dur": 17.116, + "args": { + "External id": 1435358,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678781.420, "dur": 37.771, + "args": { + "External id": 1435359,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852678822.358, "dur": 32.984, + "args": { + "External id": 1435360,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852678906.550, "dur": 324.247, + "args": { + "External id": 1435361,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852679004.510, "dur": 7.651, + "args": { + "External id": 1435362,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852679014.938, "dur": 4.317, + "args": { + "External id": 1435363,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852679020.697, "dur": 3.243, + "args": { + "External id": 1435364,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852679025.429, "dur": 2.565, + "args": { + "External id": 1435365,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852679111.134, "dur": 5.405, + "args": { + "External id": 1435366,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852679113.058, "dur": 3.156, + "args": { + "External id": 1435367,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852679118.470, "dur": 35.835, + "args": { + "External id": 1435368,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852679124.277, "dur": 3.596, + "args": { + "External id": 1435369,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852679155.936, "dur": 4.407, + "args": { + "External id": 1435370,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852679159.543, "dur": 0.708, + "args": { + "External id": 1435371,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852679161.584, "dur": 19.679, + "args": { + "External id": 1435372,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852679165.538, "dur": 2.059, + "args": { + "External id": 1435373,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852679280.091, "dur": 27.951, + "args": { + "External id": 1435374,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852679328.136, "dur": 17.018, + "args": { + "External id": 1435375,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852679353.706, "dur": 49.383, + "args": { + "External id": 1435376,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852679410.825, "dur": 40.345, + "args": { + "External id": 1435377,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852679478.077, "dur": 30.440, + "args": { + "External id": 1435378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852679514.975, "dur": 35.599, + "args": { + "External id": 1435379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852679557.233, "dur": 29.287, + "args": { + "External id": 1435380,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852679598.036, "dur": 28.214, + "args": { + "External id": 1435381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852679653.613, "dur": 25.576, + "args": { + "External id": 1435382,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852679700.134, "dur": 25.261, + "args": { + "External id": 1435383,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852679745.901, "dur": 18.237, + "args": { + "External id": 1435384,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852679783.432, "dur": 18.234, + "args": { + "External id": 1435385,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852679815.551, "dur": 16.898, + "args": { + "External id": 1435386,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679909.063, "dur": 15.212, + "args": { + "External id": 1435387,"Record function id": 0, "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679912.116, "dur": 11.176, + "args": { + "External id": 1435388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679916.816, "dur": 5.574, + "args": { + "External id": 1435389,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679918.230, "dur": 4.049, + "args": { + "External id": 1435390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679928.231, "dur": 5.368, + "args": { + "External id": 1435391,"Record function id": 0, "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679929.573, "dur": 3.542, + "args": { + "External id": 1435392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679930.611, "dur": 1.906, + "args": { + "External id": 1435393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679931.462, "dur": 0.975, + "args": { + "External id": 1435394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679937.038, "dur": 6.243, + "args": { + "External id": 1435395,"Record function id": 0, "Ev Idx": 5378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679938.455, "dur": 4.412, + "args": { + "External id": 1435396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679939.200, "dur": 3.283, + "args": { + "External id": 1435397,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679939.758, "dur": 2.634, + "args": { + "External id": 1435398,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679946.730, "dur": 5.230, + "args": { + "External id": 1435399,"Record function id": 0, "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679948.853, "dur": 2.705, + "args": { + "External id": 1435400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679949.634, "dur": 1.434, + "args": { + "External id": 1435401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679949.951, "dur": 1.048, + "args": { + "External id": 1435402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679955.024, "dur": 3.633, + "args": { + "External id": 1435403,"Record function id": 0, "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679956.116, "dur": 2.143, + "args": { + "External id": 1435404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679956.886, "dur": 0.928, + "args": { + "External id": 1435405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679957.164, "dur": 0.588, + "args": { + "External id": 1435406,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679961.746, "dur": 5.768, + "args": { + "External id": 1435407,"Record function id": 0, "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679962.890, "dur": 4.189, + "args": { + "External id": 1435408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679963.344, "dur": 3.191, + "args": { + "External id": 1435409,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679965.746, "dur": 0.679, + "args": { + "External id": 1435410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679970.808, "dur": 3.580, + "args": { + "External id": 1435411,"Record function id": 0, "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679972.001, "dur": 1.951, + "args": { + "External id": 1435412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679972.610, "dur": 0.901, + "args": { + "External id": 1435413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852679972.877, "dur": 0.567, + "args": { + "External id": 1435414,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679997.565, "dur": 7.160, + "args": { + "External id": 1435415,"Record function id": 0, "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852679999.639, "dur": 4.424, + "args": { + "External id": 1435416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852680000.757, "dur": 2.414, + "args": { + "External id": 1435417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852680001.495, "dur": 1.472, + "args": { + "External id": 1435418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852680008.023, "dur": 4.681, + "args": { + "External id": 1435419,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852680009.460, "dur": 2.840, + "args": { + "External id": 1435420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852680010.283, "dur": 1.576, + "args": { + "External id": 1435421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852680010.837, "dur": 0.954, + "args": { + "External id": 1435422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852680017.834, "dur": 65631.041, + "args": { + "External id": 1435423,"Record function id": 0, "Sequence number": 15348663, "Fwd thread id": 1, "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852680019.595, "dur": 65620.429, + "args": { + "External id": 1435424,"Sequence number": 15348663, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5407 + } + }, + { + "ph": "f", "id": 219, "pid": 2338706, "tid": 2379422, "ts": 6413852680019.595, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413852680050.741, "dur": 91.850, + "args": { + "External id": 1435425,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413852680152.660, "dur": 73.610, + "args": { + "External id": 1435426,"Record function id": 0, "Ev Idx": 5409 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413852680232.757, "dur": 65398.347, + "args": { + "External id": 1435427,"Record function id": 0, "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852680327.627, "dur": 8.064, + "args": { + "External id": 1435428,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852680345.954, "dur": 7.334, + "args": { + "External id": 1435429,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852680368.180, "dur": 64274.882, + "args": { + "External id": 1435430,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852680383.417, "dur": 64245.962, + "args": { + "External id": 1435431,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852680472.194, "dur": 17.932, + "args": { + "External id": 1435432,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852680512.557, "dur": 64070.443, + "args": { + "External id": 1435433,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852680517.189, "dur": 64064.791, + "args": { + "External id": 1435434,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852680522.336, "dur": 10.398, + "args": { + "External id": 1435435,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852680534.743, "dur": 64041.808, + "args": { + "External id": 1435436,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852744752.287, "dur": 12.591, + "args": { + "External id": 1435437,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852744755.997, "dur": 8.428, + "args": { + "External id": 1435438,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852744795.517, "dur": 507.979, + "args": { + "External id": 1435439,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852744830.488, "dur": 466.711, + "args": { + "External id": 1435440,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5423, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852744843.335, "dur": 446.000, + "args": { + "External id": 1435441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852745331.237, "dur": 2.494, + "args": { + "External id": 1435442,"Record function id": 0, "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": 5425, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745406.293, "dur": 7.283, + "args": { + "External id": 1435443,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745459.542, "dur": 1.223, + "args": { + "External id": 1435444,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745476.698, "dur": 3.829, + "args": { + "External id": 1435445,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745493.343, "dur": 1.029, + "args": { + "External id": 1435446,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745509.680, "dur": 0.783, + "args": { + "External id": 1435447,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745521.682, "dur": 1.053, + "args": { + "External id": 1435448,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745534.003, "dur": 2.785, + "args": { + "External id": 1435449,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745547.244, "dur": 2.249, + "args": { + "External id": 1435450,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745563.482, "dur": 0.821, + "args": { + "External id": 1435451,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852745663.866, "dur": 3112.314, + "args": { + "External id": 1435452,"Record function id": 0, "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413852745687.689, "dur": 1189.933, + "args": { + "External id": 1435453,"Record function id": 0, "Ev Idx": 5436 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413852745703.901, "dur": 455.632, + "args": { + "External id": 1435454,"Record function id": 0, "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745796.851, "dur": 3.916, + "args": { + "External id": 1435455,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745804.474, "dur": 0.965, + "args": { + "External id": 1435456,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745807.359, "dur": 2.885, + "args": { + "External id": 1435457,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745812.307, "dur": 0.668, + "args": { + "External id": 1435458,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745814.817, "dur": 1.200, + "args": { + "External id": 1435459,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745819.985, "dur": 0.766, + "args": { + "External id": 1435460,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745822.380, "dur": 1.853, + "args": { + "External id": 1435461,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745825.958, "dur": 0.738, + "args": { + "External id": 1435462,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745828.591, "dur": 0.643, + "args": { + "External id": 1435463,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852745833.151, "dur": 0.600, + "args": { + "External id": 1435464,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852745852.216, "dur": 261.920, + "args": { + "External id": 1435465,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852745914.711, "dur": 192.312, + "args": { + "External id": 1435466,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852745932.560, "dur": 18.026, + "args": { + "External id": 1435467,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852745954.253, "dur": 89.881, + "args": { + "External id": 1435468,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852745957.118, "dur": 86.551, + "args": { + "External id": 1435469,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852745961.180, "dur": 7.401, + "args": { + "External id": 1435470,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852745970.119, "dur": 72.348, + "args": { + "External id": 1435471,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 2338706, "tid": 2379422, + "ts": 6413852746265.583, "dur": 603.814, + "args": { + "External id": 1435472,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413852746286.596, "dur": 570.790, + "args": { + "External id": 1435473,"Record function id": 0, "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852746358.538, "dur": 6.401, + "args": { + "External id": 1435474,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852746380.905, "dur": 35.987, + "args": { + "External id": 1435475,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746386.544, "dur": 2.056, + "args": { + "External id": 1435476,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746390.851, "dur": 1.610, + "args": { + "External id": 1435477,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746394.034, "dur": 0.569, + "args": { + "External id": 1435478,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746396.365, "dur": 0.458, + "args": { + "External id": 1435479,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746400.030, "dur": 0.324, + "args": { + "External id": 1435480,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746402.275, "dur": 2.558, + "args": { + "External id": 1435481,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746406.641, "dur": 0.397, + "args": { + "External id": 1435482,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746410.193, "dur": 0.305, + "args": { + "External id": 1435483,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746412.101, "dur": 0.390, + "args": { + "External id": 1435484,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852746428.460, "dur": 43.877, + "args": { + "External id": 1435485,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413852746504.283, "dur": 117.782, + "args": { + "External id": 1435486,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 5469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852746515.630, "dur": 3.478, + "args": { + "External id": 1435487,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413852746525.468, "dur": 12.280, + "args": { + "External id": 1435488,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413852746531.658, "dur": 5.642, + "args": { + "External id": 1435489,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 5472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746535.420, "dur": 0.643, + "args": { + "External id": 1435490,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413852746545.043, "dur": 27.815, + "args": { + "External id": 1435491,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746547.428, "dur": 0.454, + "args": { + "External id": 1435492,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746551.070, "dur": 0.371, + "args": { + "External id": 1435493,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746552.814, "dur": 2.554, + "args": { + "External id": 1435494,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746557.091, "dur": 1.279, + "args": { + "External id": 1435495,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746560.138, "dur": 0.318, + "args": { + "External id": 1435496,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746562.003, "dur": 0.334, + "args": { + "External id": 1435497,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746565.343, "dur": 0.374, + "args": { + "External id": 1435498,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746567.078, "dur": 0.294, + "args": { + "External id": 1435499,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852746568.871, "dur": 0.306, + "args": { + "External id": 1435500,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852746584.031, "dur": 30.734, + "args": { + "External id": 1435501,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 5484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852746665.236, "dur": 123.462, + "args": { + "External id": 1435502,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 5485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852746695.263, "dur": 90.091, + "args": { + "External id": 1435503,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5486, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852746704.381, "dur": 76.494, + "args": { + "External id": 1435504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 5487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852746806.117, "dur": 1.843, + "args": { + "External id": 1435505,"Record function id": 0, "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": 5488, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852746885.279, "dur": 1868.672, + "args": { + "External id": 1435506,"Sequence number": 15348662, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5489 + } + }, + { + "ph": "f", "id": 220, "pid": 2338706, "tid": 2379422, "ts": 6413852746885.279, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747024.394, "dur": 143.710, + "args": { + "External id": 1435507,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852747222.322, "dur": 46.585, + "args": { + "External id": 1435508,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747288.516, "dur": 50.899, + "args": { + "External id": 1435509,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747351.153, "dur": 31.263, + "args": { + "External id": 1435510,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747388.468, "dur": 30.190, + "args": { + "External id": 1435511,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747425.098, "dur": 26.259, + "args": { + "External id": 1435512,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747458.777, "dur": 29.203, + "args": { + "External id": 1435513,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852747515.738, "dur": 25.307, + "args": { + "External id": 1435514,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852747563.794, "dur": 29.340, + "args": { + "External id": 1435515,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852747617.153, "dur": 20.738, + "args": { + "External id": 1435516,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852747654.380, "dur": 16.267, + "args": { + "External id": 1435517,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747678.963, "dur": 35.810, + "args": { + "External id": 1435518,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852747718.182, "dur": 31.575, + "args": { + "External id": 1435519,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852747806.454, "dur": 320.464, + "args": { + "External id": 1435520,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852747893.556, "dur": 6.298, + "args": { + "External id": 1435521,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852747902.154, "dur": 2.522, + "args": { + "External id": 1435522,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852747906.149, "dur": 1.967, + "args": { + "External id": 1435523,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852747909.307, "dur": 2.095, + "args": { + "External id": 1435524,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852747957.591, "dur": 6.588, + "args": { + "External id": 1435525,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852747959.542, "dur": 4.401, + "args": { + "External id": 1435526,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852747966.262, "dur": 54.072, + "args": { + "External id": 1435527,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852747971.599, "dur": 3.731, + "args": { + "External id": 1435528,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852748025.007, "dur": 2.043, + "args": { + "External id": 1435529,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852748026.031, "dur": 0.931, + "args": { + "External id": 1435530,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852748028.012, "dur": 17.570, + "args": { + "External id": 1435531,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852748032.210, "dur": 0.666, + "args": { + "External id": 1435532,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852748176.484, "dur": 31.442, + "args": { + "External id": 1435533,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852748239.987, "dur": 27.805, + "args": { + "External id": 1435534,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852748280.587, "dur": 55.085, + "args": { + "External id": 1435535,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852748342.719, "dur": 42.128, + "args": { + "External id": 1435536,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852748395.066, "dur": 19.610, + "args": { + "External id": 1435537,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852748423.305, "dur": 30.863, + "args": { + "External id": 1435538,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852748461.432, "dur": 27.665, + "args": { + "External id": 1435539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852748495.476, "dur": 28.731, + "args": { + "External id": 1435540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852748549.532, "dur": 25.001, + "args": { + "External id": 1435541,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852748594.596, "dur": 24.432, + "args": { + "External id": 1435542,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852748639.538, "dur": 18.574, + "args": { + "External id": 1435543,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852748674.853, "dur": 14.877, + "args": { + "External id": 1435544,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852748706.908, "dur": 17.267, + "args": { + "External id": 1435545,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748799.237, "dur": 16.063, + "args": { + "External id": 1435546,"Record function id": 0, "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748802.626, "dur": 11.650, + "args": { + "External id": 1435547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748806.766, "dur": 6.572, + "args": { + "External id": 1435548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748808.415, "dur": 4.823, + "args": { + "External id": 1435549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748819.266, "dur": 5.275, + "args": { + "External id": 1435550,"Record function id": 0, "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748821.165, "dur": 2.807, + "args": { + "External id": 1435551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748821.910, "dur": 1.587, + "args": { + "External id": 1435552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748822.500, "dur": 0.909, + "args": { + "External id": 1435553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748827.877, "dur": 6.847, + "args": { + "External id": 1435554,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748829.394, "dur": 4.829, + "args": { + "External id": 1435555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748830.024, "dur": 3.648, + "args": { + "External id": 1435556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748830.673, "dur": 2.892, + "args": { + "External id": 1435557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748838.064, "dur": 4.092, + "args": { + "External id": 1435558,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748839.341, "dur": 2.369, + "args": { + "External id": 1435559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748839.863, "dur": 1.274, + "args": { + "External id": 1435560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748840.157, "dur": 0.914, + "args": { + "External id": 1435561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748845.370, "dur": 3.954, + "args": { + "External id": 1435562,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748846.461, "dur": 2.429, + "args": { + "External id": 1435563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748847.152, "dur": 1.145, + "args": { + "External id": 1435564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748847.430, "dur": 0.792, + "args": { + "External id": 1435565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748852.534, "dur": 4.734, + "args": { + "External id": 1435566,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748854.021, "dur": 2.800, + "args": { + "External id": 1435567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748854.604, "dur": 1.749, + "args": { + "External id": 1435568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748855.227, "dur": 1.050, + "args": { + "External id": 1435569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748860.493, "dur": 4.331, + "args": { + "External id": 1435570,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748862.021, "dur": 2.334, + "args": { + "External id": 1435571,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748862.703, "dur": 1.192, + "args": { + "External id": 1435572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748863.126, "dur": 0.708, + "args": { + "External id": 1435573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748867.961, "dur": 4.076, + "args": { + "External id": 1435574,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748869.421, "dur": 2.180, + "args": { + "External id": 1435575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748870.006, "dur": 1.009, + "args": { + "External id": 1435576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748870.271, "dur": 0.661, + "args": { + "External id": 1435577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748875.591, "dur": 6.284, + "args": { + "External id": 1435578,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852748877.032, "dur": 4.405, + "args": { + "External id": 1435579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748877.506, "dur": 3.412, + "args": { + "External id": 1435580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852748880.072, "dur": 0.718, + "args": { + "External id": 1435581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852748886.611, "dur": 61204.059, + "args": { + "External id": 1435582,"Record function id": 0, "Sequence number": 15348661, "Fwd thread id": 1, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852748888.711, "dur": 61158.188, + "args": { + "External id": 1435583,"Sequence number": 15348661, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5566 + } + }, + { + "ph": "f", "id": 221, "pid": 2338706, "tid": 2379422, "ts": 6413852748888.711, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413852748917.694, "dur": 43.180, + "args": { + "External id": 1435584,"Record function id": 0, "Ev Idx": 5567 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413852748969.054, "dur": 131.389, + "args": { + "External id": 1435585,"Record function id": 0, "Ev Idx": 5568 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413852749109.810, "dur": 60928.105, + "args": { + "External id": 1435586,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852749208.079, "dur": 8.072, + "args": { + "External id": 1435587,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852749226.783, "dur": 7.021, + "args": { + "External id": 1435588,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852749248.939, "dur": 59924.115, + "args": { + "External id": 1435589,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852749263.169, "dur": 59895.637, + "args": { + "External id": 1435590,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852749353.915, "dur": 18.625, + "args": { + "External id": 1435591,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852749396.853, "dur": 59714.803, + "args": { + "External id": 1435592,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852749399.501, "dur": 59710.903, + "args": { + "External id": 1435593,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852749404.573, "dur": 11.705, + "args": { + "External id": 1435594,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852749418.551, "dur": 59686.535, + "args": { + "External id": 1435595,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852809284.511, "dur": 12.758, + "args": { + "External id": 1435596,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852809288.466, "dur": 8.398, + "args": { + "External id": 1435597,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852809329.849, "dur": 387.176, + "args": { + "External id": 1435598,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852809364.553, "dur": 347.586, + "args": { + "External id": 1435599,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5582, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852809377.469, "dur": 329.441, + "args": { + "External id": 1435600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852809740.042, "dur": 2.192, + "args": { + "External id": 1435601,"Record function id": 0, "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": 5584, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809800.322, "dur": 6.648, + "args": { + "External id": 1435602,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809852.546, "dur": 1.641, + "args": { + "External id": 1435603,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809870.546, "dur": 3.709, + "args": { + "External id": 1435604,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809886.959, "dur": 0.859, + "args": { + "External id": 1435605,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809900.522, "dur": 0.772, + "args": { + "External id": 1435606,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809912.774, "dur": 0.710, + "args": { + "External id": 1435607,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809926.266, "dur": 3.012, + "args": { + "External id": 1435608,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809940.075, "dur": 2.093, + "args": { + "External id": 1435609,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852809952.434, "dur": 0.921, + "args": { + "External id": 1435610,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852810110.494, "dur": 2447.443, + "args": { + "External id": 1435611,"Record function id": 0, "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413852810134.083, "dur": 483.314, + "args": { + "External id": 1435612,"Record function id": 0, "Ev Idx": 5595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413852810151.582, "dur": 355.260, + "args": { + "External id": 1435613,"Record function id": 0, "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810253.466, "dur": 4.759, + "args": { + "External id": 1435614,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810261.771, "dur": 0.921, + "args": { + "External id": 1435615,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810266.880, "dur": 3.217, + "args": { + "External id": 1435616,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810272.330, "dur": 0.966, + "args": { + "External id": 1435617,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810275.108, "dur": 0.904, + "args": { + "External id": 1435618,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810277.597, "dur": 0.994, + "args": { + "External id": 1435619,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810282.598, "dur": 1.903, + "args": { + "External id": 1435620,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810286.331, "dur": 0.890, + "args": { + "External id": 1435621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810289.222, "dur": 1.314, + "args": { + "External id": 1435622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852810292.309, "dur": 0.657, + "args": { + "External id": 1435623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 5606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852810314.391, "dur": 160.758, + "args": { + "External id": 1435624,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852810332.018, "dur": 138.334, + "args": { + "External id": 1435625,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 5608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852810352.435, "dur": 18.281, + "args": { + "External id": 1435626,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852810374.633, "dur": 64.904, + "args": { + "External id": 1435627,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 5610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852810377.372, "dur": 61.827, + "args": { + "External id": 1435628,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 5611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852810381.365, "dur": 7.324, + "args": { + "External id": 1435629,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852810390.431, "dur": 48.171, + "args": { + "External id": 1435630,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 5613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852810624.512, "dur": 1908.101, + "args": { + "External id": 1435631,"Sequence number": 15348660, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5614 + } + }, + { + "ph": "f", "id": 222, "pid": 2338706, "tid": 2379422, "ts": 6413852810624.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852810734.728, "dur": 102.689, + "args": { + "External id": 1435632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 5615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852810884.644, "dur": 42.296, + "args": { + "External id": 1435633,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 5616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413852810947.043, "dur": 70.145, + "args": { + "External id": 1435634,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 5617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852811030.651, "dur": 71.817, + "args": { + "External id": 1435635,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852811114.832, "dur": 35.794, + "args": { + "External id": 1435636,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852811157.783, "dur": 27.295, + "args": { + "External id": 1435637,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 5620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852811194.285, "dur": 29.122, + "args": { + "External id": 1435638,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 5621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852811253.701, "dur": 27.828, + "args": { + "External id": 1435639,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 5622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852811300.933, "dur": 29.060, + "args": { + "External id": 1435640,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852811356.000, "dur": 20.106, + "args": { + "External id": 1435641,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852811390.483, "dur": 13.876, + "args": { + "External id": 1435642,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852811414.428, "dur": 35.656, + "args": { + "External id": 1435643,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852811453.601, "dur": 30.727, + "args": { + "External id": 1435644,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413852811515.297, "dur": 345.780, + "args": { + "External id": 1435645,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852811603.085, "dur": 7.578, + "args": { + "External id": 1435646,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852811612.916, "dur": 2.904, + "args": { + "External id": 1435647,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852811617.067, "dur": 4.741, + "args": { + "External id": 1435648,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852811695.934, "dur": 10.662, + "args": { + "External id": 1435649,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852811749.693, "dur": 6.542, + "args": { + "External id": 1435650,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852811753.133, "dur": 2.921, + "args": { + "External id": 1435651,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852811758.394, "dur": 29.805, + "args": { + "External id": 1435652,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852811763.934, "dur": 1.596, + "args": { + "External id": 1435653,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413852811791.872, "dur": 1.374, + "args": { + "External id": 1435654,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852811792.644, "dur": 0.513, + "args": { + "External id": 1435655,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 5638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413852811794.739, "dur": 18.653, + "args": { + "External id": 1435656,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852811798.586, "dur": 0.615, + "args": { + "External id": 1435657,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852811908.915, "dur": 28.319, + "args": { + "External id": 1435658,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852811956.814, "dur": 15.335, + "args": { + "External id": 1435659,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852812011.301, "dur": 89.118, + "args": { + "External id": 1435660,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852812112.270, "dur": 46.069, + "args": { + "External id": 1435661,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852812170.041, "dur": 22.576, + "args": { + "External id": 1435662,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 5645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852812198.434, "dur": 30.201, + "args": { + "External id": 1435663,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 5646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852812235.197, "dur": 26.883, + "args": { + "External id": 1435664,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 5647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413852812270.482, "dur": 30.309, + "args": { + "External id": 1435665,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 5648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413852812329.902, "dur": 25.905, + "args": { + "External id": 1435666,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 5649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852812376.908, "dur": 23.628, + "args": { + "External id": 1435667,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852812417.570, "dur": 18.416, + "args": { + "External id": 1435668,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 5651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413852812453.465, "dur": 15.259, + "args": { + "External id": 1435669,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413852812482.199, "dur": 18.285, + "args": { + "External id": 1435670,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 5653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812581.091, "dur": 15.938, + "args": { + "External id": 1435671,"Record function id": 0, "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812584.670, "dur": 11.454, + "args": { + "External id": 1435672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812589.178, "dur": 5.859, + "args": { + "External id": 1435673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812590.615, "dur": 4.326, + "args": { + "External id": 1435674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812600.897, "dur": 7.101, + "args": { + "External id": 1435675,"Record function id": 0, "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812602.653, "dur": 4.860, + "args": { + "External id": 1435676,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812603.325, "dur": 3.527, + "args": { + "External id": 1435677,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812603.858, "dur": 2.871, + "args": { + "External id": 1435678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812611.341, "dur": 4.672, + "args": { + "External id": 1435679,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812612.889, "dur": 2.696, + "args": { + "External id": 1435680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812613.596, "dur": 1.569, + "args": { + "External id": 1435681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812614.295, "dur": 0.783, + "args": { + "External id": 1435682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 5665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812619.286, "dur": 4.678, + "args": { + "External id": 1435683,"Record function id": 0, "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812621.098, "dur": 2.431, + "args": { + "External id": 1435684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812621.838, "dur": 1.239, + "args": { + "External id": 1435685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812622.308, "dur": 0.701, + "args": { + "External id": 1435686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 5669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812626.993, "dur": 4.479, + "args": { + "External id": 1435687,"Record function id": 0, "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812628.701, "dur": 2.360, + "args": { + "External id": 1435688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812629.319, "dur": 1.123, + "args": { + "External id": 1435689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812629.619, "dur": 0.759, + "args": { + "External id": 1435690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812634.552, "dur": 6.668, + "args": { + "External id": 1435691,"Record function id": 0, "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812636.062, "dur": 4.734, + "args": { + "External id": 1435692,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812636.796, "dur": 3.549, + "args": { + "External id": 1435693,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812639.167, "dur": 1.066, + "args": { + "External id": 1435694,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 5677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812644.523, "dur": 4.660, + "args": { + "External id": 1435695,"Record function id": 0, "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812646.445, "dur": 2.314, + "args": { + "External id": 1435696,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812647.080, "dur": 1.153, + "args": { + "External id": 1435697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812647.529, "dur": 0.631, + "args": { + "External id": 1435698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812652.535, "dur": 4.561, + "args": { + "External id": 1435699,"Record function id": 0, "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812654.269, "dur": 2.418, + "args": { + "External id": 1435700,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812654.944, "dur": 1.221, + "args": { + "External id": 1435701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812655.338, "dur": 0.753, + "args": { + "External id": 1435702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 5685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812660.316, "dur": 7.182, + "args": { + "External id": 1435703,"Record function id": 0, "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852812661.737, "dur": 5.335, + "args": { + "External id": 1435704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812662.393, "dur": 4.292, + "args": { + "External id": 1435705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852812663.359, "dur": 3.256, + "args": { + "External id": 1435706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 5689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852812671.910, "dur": 62510.865, + "args": { + "External id": 1435707,"Record function id": 0, "Sequence number": 15348659, "Fwd thread id": 1, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852812673.673, "dur": 62500.367, + "args": { + "External id": 1435708,"Sequence number": 15348659, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5691 + } + }, + { + "ph": "f", "id": 223, "pid": 2338706, "tid": 2379422, "ts": 6413852812673.673, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413852812702.598, "dur": 42.679, + "args": { + "External id": 1435709,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413852812753.239, "dur": 93.387, + "args": { + "External id": 1435710,"Record function id": 0, "Ev Idx": 5693 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413852812857.898, "dur": 62306.939, + "args": { + "External id": 1435711,"Record function id": 0, "Ev Idx": 5694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852812955.645, "dur": 7.577, + "args": { + "External id": 1435712,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852812972.815, "dur": 27.000, + "args": { + "External id": 1435713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 5696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852813016.333, "dur": 61245.488, + "args": { + "External id": 1435714,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852813031.539, "dur": 61216.779, + "args": { + "External id": 1435715,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 5698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852813191.510, "dur": 24.833, + "args": { + "External id": 1435716,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852813236.990, "dur": 60960.586, + "args": { + "External id": 1435717,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 5700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852813242.136, "dur": 60954.288, + "args": { + "External id": 1435718,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 5701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852813246.748, "dur": 12.942, + "args": { + "External id": 1435719,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852813261.718, "dur": 60930.010, + "args": { + "External id": 1435720,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 5703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852874373.652, "dur": 11.256, + "args": { + "External id": 1435721,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 5704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852874376.981, "dur": 7.596, + "args": { + "External id": 1435722,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852874413.809, "dur": 384.489, + "args": { + "External id": 1435723,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 5706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852874448.923, "dur": 344.569, + "args": { + "External id": 1435724,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5707, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852874461.787, "dur": 326.220, + "args": { + "External id": 1435725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 5708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852874821.317, "dur": 2.214, + "args": { + "External id": 1435726,"Record function id": 0, "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": 5709, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852874879.750, "dur": 6.736, + "args": { + "External id": 1435727,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852874930.940, "dur": 3.325, + "args": { + "External id": 1435728,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852874950.786, "dur": 1.298, + "args": { + "External id": 1435729,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852874964.910, "dur": 1.002, + "args": { + "External id": 1435730,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852874998.167, "dur": 1.491, + "args": { + "External id": 1435731,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852875015.626, "dur": 3.348, + "args": { + "External id": 1435732,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852875032.511, "dur": 0.841, + "args": { + "External id": 1435733,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852875044.660, "dur": 2.016, + "args": { + "External id": 1435734,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852875096.268, "dur": 1.448, + "args": { + "External id": 1435735,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 5718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852875199.642, "dur": 304.440, + "args": { + "External id": 1435736,"Record function id": 0, "Sequence number": 15348658, "Fwd thread id": 1, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413852875202.782, "dur": 292.088, + "args": { + "External id": 1435737,"Sequence number": 15348658, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5720 + } + }, + { + "ph": "f", "id": 224, "pid": 2338706, "tid": 2379422, "ts": 6413852875202.782, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338706, "tid": 2379422, + "ts": 6413852875331.483, "dur": 55.143, + "args": { + "External id": 1435738,"kernel_hash": "cwi477k6wdh6lokdagawsji5sufpvs7jjfv77xwkpv6wyl2co2tv", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/wi/cwi477k6wdh6lokdagawsji5sufpvs7jjfv77xwkpv6wyl2co2tv.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 5721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 2338706, "tid": 2379422, + "ts": 6413852875404.729, "dur": 29.886, + "args": { + "External id": 1435739,"kernel_hash": "cdaibgaofwvuhdtnzghakbdinq55v26czvh7dtqt726q3xahddo3", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/da/cdaibgaofwvuhdtnzghakbdinq55v26czvh7dtqt726q3xahddo3.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096, 4096], [32000, 4096], []], "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 2338706, "tid": 2379422, + "ts": 6413852875455.312, "dur": 23.642, + "args": { + "External id": 1435740,"kernel_hash": "cozpxeylo6qxtrc76ucyd7ba7bcr4ctg436exqn3bklybds2girm", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/oz/cozpxeylo6qxtrc76ucyd7ba7bcr4ctg436exqn3bklybds2girm.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 5723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852875513.811, "dur": 14.585, + "args": { + "External id": 1435741,"Record function id": 0, "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413852875516.923, "dur": 10.270, + "args": { + "External id": 1435742,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 5725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852875520.377, "dur": 5.832, + "args": { + "External id": 1435743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413852875522.248, "dur": 3.843, + "args": { + "External id": 1435744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 2338706, "tid": 2379422, + "ts": 6413852875552.171, "dur": 18607.710, + "args": { + "External id": 1435745,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338706, "tid": 2379422, + "ts": 6413852875572.346, "dur": 42.358, + "args": { + "External id": 1435746,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338706, "tid": 2379422, + "ts": 6413852875620.704, "dur": 302.629, + "args": { + "External id": 1435747,"Record function id": 0, "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338706, "tid": 2379422, + "ts": 6413852875929.473, "dur": 17916.906, + "args": { + "External id": 1435748,"Record function id": 0, "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852876109.484, "dur": 9.742, + "args": { + "External id": 1435749,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413852876131.794, "dur": 5.483, + "args": { + "External id": 1435750,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 5733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852876162.825, "dur": 16349.546, + "args": { + "External id": 1435751,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 5734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413852876182.864, "dur": 16313.992, + "args": { + "External id": 1435752,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 5735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852877109.684, "dur": 25.082, + "args": { + "External id": 1435753,"Record function id": 0, "Concrete Inputs": ["[277237]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413852877412.910, "dur": 15026.758, + "args": { + "External id": 1435754,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], [], []], "Ev Idx": 5737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413852877416.850, "dur": 15021.279, + "args": { + "External id": 1435755,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], []], "Ev Idx": 5738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852877423.462, "dur": 17.586, + "args": { + "External id": 1435756,"Record function id": 0, "Concrete Inputs": ["[277237]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413852877444.190, "dur": 14987.559, + "args": { + "External id": 1435757,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[277237], [277237], []], "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852892677.504, "dur": 12.338, + "args": { + "External id": 1435758,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1134596096], [], [], [], [], []], "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413852892681.074, "dur": 8.350, + "args": { + "External id": 1435759,"Record function id": 0, "Concrete Inputs": ["[141824512]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413852892718.192, "dur": 426.410, + "args": { + "External id": 1435760,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[141824512], [1134596096], [], [], [], []], "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852892748.578, "dur": 390.415, + "args": { + "External id": 1435761,"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": 141824512, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1134596096], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5744, "In msg nelems": 1134596096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413852892762.510, "dur": 370.420, + "args": { + "External id": 1435762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1134596096]], "Ev Idx": 5745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413852893171.736, "dur": 2.399, + "args": { + "External id": 1435763,"Record function id": 0, "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": 5746, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893235.787, "dur": 8.433, + "args": { + "External id": 1435764,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893287.494, "dur": 1.377, + "args": { + "External id": 1435765,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893304.057, "dur": 1.571, + "args": { + "External id": 1435766,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "16384512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893319.176, "dur": 0.787, + "args": { + "External id": 1435767,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "18481664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893333.574, "dur": 2.605, + "args": { + "External id": 1435768,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "19005952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893346.623, "dur": 0.714, + "args": { + "External id": 1435769,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "19530240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893358.631, "dur": 2.086, + "args": { + "External id": 1435770,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893373.115, "dur": 0.736, + "args": { + "External id": 1435771,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "21627904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893384.765, "dur": 2.639, + "args": { + "External id": 1435772,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "28967936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893398.039, "dur": 0.852, + "args": { + "External id": 1435773,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "36307968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893410.734, "dur": 0.749, + "args": { + "External id": 1435774,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893421.903, "dur": 0.635, + "args": { + "External id": 1435775,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "43648512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893436.231, "dur": 2.742, + "args": { + "External id": 1435776,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "45745664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893449.235, "dur": 0.620, + "args": { + "External id": 1435777,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "46269952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893460.239, "dur": 2.020, + "args": { + "External id": 1435778,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "46794240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893474.266, "dur": 0.603, + "args": { + "External id": 1435779,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893485.727, "dur": 2.892, + "args": { + "External id": 1435780,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "48891904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893500.976, "dur": 0.786, + "args": { + "External id": 1435781,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "56231936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893512.119, "dur": 0.729, + "args": { + "External id": 1435782,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "63571968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893522.877, "dur": 0.538, + "args": { + "External id": 1435783,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893534.762, "dur": 3.683, + "args": { + "External id": 1435784,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "70912512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893548.672, "dur": 0.580, + "args": { + "External id": 1435785,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73009664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893560.826, "dur": 1.180, + "args": { + "External id": 1435786,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73533952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893585.012, "dur": 0.754, + "args": { + "External id": 1435787,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "74058240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893598.466, "dur": 2.640, + "args": { + "External id": 1435788,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893611.961, "dur": 0.707, + "args": { + "External id": 1435789,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "76155904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893623.069, "dur": 1.657, + "args": { + "External id": 1435790,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "83495936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893637.931, "dur": 0.852, + "args": { + "External id": 1435791,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "90835968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893649.587, "dur": 3.949, + "args": { + "External id": 1435792,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893664.419, "dur": 0.927, + "args": { + "External id": 1435793,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "98176512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893676.558, "dur": 0.894, + "args": { + "External id": 1435794,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100273664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893687.876, "dur": 0.813, + "args": { + "External id": 1435795,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100797952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893701.400, "dur": 3.082, + "args": { + "External id": 1435796,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "101322240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893715.225, "dur": 0.797, + "args": { + "External id": 1435797,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893727.307, "dur": 1.888, + "args": { + "External id": 1435798,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "103419904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893740.489, "dur": 0.986, + "args": { + "External id": 1435799,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "110759936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893752.852, "dur": 2.720, + "args": { + "External id": 1435800,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "118099968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893765.791, "dur": 0.918, + "args": { + "External id": 1435801,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413852893778.208, "dur": 1.235, + "args": { + "External id": 1435802,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "125440512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854028999.314, "dur": 167.957, + "args": { + "External id": 1435803,"Record function id": 0, "Sequence number": 15349113, "Fwd thread id": 1, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854029010.825, "dur": 142.580, + "args": { + "External id": 1435804,"Sequence number": 15349113, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5787 + } + }, + { + "ph": "f", "id": 225, "pid": 2338706, "tid": 2379422, "ts": 6413854029010.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2379422, + "ts": 6413854029021.468, "dur": 129.548, + "args": { + "External id": 1435805,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854029179.405, "dur": 319.605, + "args": { + "External id": 1435806,"Record function id": 0, "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854029286.888, "dur": 122.246, + "args": { + "External id": 1435807,"Record function id": 0, "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 2338706, "tid": 2379422, + "ts": 6413854029328.949, "dur": 66.982, + "args": { + "External id": 1435808,"Record function id": 0, "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854029415.559, "dur": 2.781, + "args": { + "External id": 1435809,"Sequence number": 15349112, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5792 + } + }, + { + "ph": "f", "id": 226, "pid": 2338706, "tid": 2379422, "ts": 6413854029415.559, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854029424.847, "dur": 65.437, + "args": { + "External id": 1435810,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854029431.584, "dur": 58.192, + "args": { + "External id": 1435811,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854029445.414, "dur": 6.270, + "args": { + "External id": 1435812,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854029509.584, "dur": 38359.739, + "args": { + "External id": 1435813,"Record function id": 0, "Sequence number": 15349110, "Fwd thread id": 1, "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854029512.714, "dur": 38340.650, + "args": { + "External id": 1435814,"Sequence number": 15349110, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5797 + } + }, + { + "ph": "f", "id": 227, "pid": 2338706, "tid": 2379422, "ts": 6413854029512.714, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854029572.895, "dur": 5.466, + "args": { + "External id": 1435815,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854029582.865, "dur": 37902.452, + "args": { + "External id": 1435816,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854029586.148, "dur": 37898.823, + "args": { + "External id": 1435817,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854029590.709, "dur": 7.402, + "args": { + "External id": 1435818,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854029601.328, "dur": 37881.958, + "args": { + "External id": 1435819,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338706, "tid": 2379422, + "ts": 6413854067490.944, "dur": 1.047, + "args": { + "External id": 1435820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854067497.710, "dur": 4.323, + "args": { + "External id": 1435821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854067500.013, "dur": 1.640, + "args": { + "External id": 1435822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2379422, + "ts": 6413854067510.320, "dur": 35.685, + "args": { + "External id": 1435823,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338706, "tid": 2379422, + "ts": 6413854067557.782, "dur": 56.368, + "args": { + "External id": 1435824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2379422, + "ts": 6413854067560.698, "dur": 53.250, + "args": { + "External id": 1435825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2379422, + "ts": 6413854067563.478, "dur": 50.103, + "args": { + "External id": 1435826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854067884.806, "dur": 24.316, + "args": { + "External id": 1435827,"Record function id": 0, "Sequence number": 15349109, "Fwd thread id": 1, "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854067887.156, "dur": 17.107, + "args": { + "External id": 1435828,"Sequence number": 15349109, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 5811 + } + }, + { + "ph": "f", "id": 228, "pid": 2338706, "tid": 2379422, "ts": 6413854067887.156, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854067893.670, "dur": 10.334, + "args": { + "External id": 1435829,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854067896.786, "dur": 7.069, + "args": { + "External id": 1435830,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854067913.515, "dur": 189.104, + "args": { + "External id": 1435831,"Record function id": 0, "Sequence number": 15349108, "Fwd thread id": 1, "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854067914.700, "dur": 176.427, + "args": { + "External id": 1435832,"Sequence number": 15349108, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5815 + } + }, + { + "ph": "f", "id": 229, "pid": 2338706, "tid": 2379422, "ts": 6413854067914.700, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854067920.620, "dur": 169.818, + "args": { + "External id": 1435833,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 5816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854067932.319, "dur": 41.265, + "args": { + "External id": 1435834,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854067935.900, "dur": 8.608, + "args": { + "External id": 1435835,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854067947.437, "dur": 25.859, + "args": { + "External id": 1435836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854067950.842, "dur": 21.835, + "args": { + "External id": 1435837,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854067989.817, "dur": 8.186, + "args": { + "External id": 1435838,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854067995.218, "dur": 2.136, + "args": { + "External id": 1435839,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854067999.575, "dur": 89.350, + "args": { + "External id": 1435840,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068110.398, "dur": 81.464, + "args": { + "External id": 1435841,"Record function id": 0, "Sequence number": 15349107, "Fwd thread id": 1, "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068112.198, "dur": 74.811, + "args": { + "External id": 1435842,"Sequence number": 15349107, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5825 + } + }, + { + "ph": "f", "id": 230, "pid": 2338706, "tid": 2379422, "ts": 6413854068112.198, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854068117.637, "dur": 69.135, + "args": { + "External id": 1435843,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854068122.525, "dur": 27.028, + "args": { + "External id": 1435844,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854068124.776, "dur": 4.136, + "args": { + "External id": 1435845,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068129.853, "dur": 19.421, + "args": { + "External id": 1435846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068132.616, "dur": 16.209, + "args": { + "External id": 1435847,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854068154.415, "dur": 9.419, + "args": { + "External id": 1435848,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 5831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854068161.245, "dur": 1.529, + "args": { + "External id": 1435849,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068164.865, "dur": 21.389, + "args": { + "External id": 1435850,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068195.993, "dur": 258.018, + "args": { + "External id": 1435851,"Record function id": 0, "Sequence number": 15349106, "Fwd thread id": 1, "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068197.370, "dur": 250.789, + "args": { + "External id": 1435852,"Sequence number": 15349106, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5835 + } + }, + { + "ph": "f", "id": 231, "pid": 2338706, "tid": 2379422, "ts": 6413854068197.370, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854068200.092, "dur": 247.665, + "args": { + "External id": 1435853,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854068202.793, "dur": 21.607, + "args": { + "External id": 1435854,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854068204.642, "dur": 3.470, + "args": { + "External id": 1435855,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068208.767, "dur": 15.365, + "args": { + "External id": 1435856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068210.657, "dur": 13.022, + "args": { + "External id": 1435857,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854068228.583, "dur": 7.621, + "args": { + "External id": 1435858,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854068231.597, "dur": 4.333, + "args": { + "External id": 1435859,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068237.049, "dur": 209.689, + "args": { + "External id": 1435860,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068458.874, "dur": 120.461, + "args": { + "External id": 1435861,"Record function id": 0, "Sequence number": 15349105, "Fwd thread id": 1, "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068460.072, "dur": 112.514, + "args": { + "External id": 1435862,"Sequence number": 15349105, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5845 + } + }, + { + "ph": "f", "id": 232, "pid": 2338706, "tid": 2379422, "ts": 6413854068460.072, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854068462.763, "dur": 109.510, + "args": { + "External id": 1435863,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854068464.519, "dur": 20.809, + "args": { + "External id": 1435864,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854068466.352, "dur": 2.069, + "args": { + "External id": 1435865,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068469.272, "dur": 15.807, + "args": { + "External id": 1435866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068471.568, "dur": 13.107, + "args": { + "External id": 1435867,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854068486.478, "dur": 3.483, + "args": { + "External id": 1435868,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854068488.962, "dur": 0.755, + "args": { + "External id": 1435869,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068516.618, "dur": 54.509, + "args": { + "External id": 1435870,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068584.783, "dur": 41.106, + "args": { + "External id": 1435871,"Record function id": 0, "Sequence number": 15349104, "Fwd thread id": 1, "Ev Idx": 5854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854068586.473, "dur": 1.019, + "args": { + "External id": 1435872,"Sequence number": 15349104, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5855 + } + }, + { + "ph": "f", "id": 233, "pid": 2338706, "tid": 2379422, "ts": 6413854068586.473, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854068591.457, "dur": 29.006, + "args": { + "External id": 1435873,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854068594.128, "dur": 25.899, + "args": { + "External id": 1435874,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854068601.288, "dur": 0.863, + "args": { + "External id": 1435875,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854068631.441, "dur": 2328.667, + "args": { + "External id": 1435876,"Record function id": 0, "Sequence number": 15349102, "Fwd thread id": 1, "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854068633.586, "dur": 2279.096, + "args": { + "External id": 1435877,"Sequence number": 15349102, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5860 + } + }, + { + "ph": "f", "id": 234, "pid": 2338706, "tid": 2379422, "ts": 6413854068633.586, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854068678.190, "dur": 2.987, + "args": { + "External id": 1435878,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854068684.144, "dur": 1991.013, + "args": { + "External id": 1435879,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854068686.116, "dur": 1988.692, + "args": { + "External id": 1435880,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854068693.095, "dur": 6.658, + "args": { + "External id": 1435881,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854068700.772, "dur": 1972.864, + "args": { + "External id": 1435882,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338706, "tid": 2379422, + "ts": 6413854070679.550, "dur": 0.380, + "args": { + "External id": 1435883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854070684.027, "dur": 3.118, + "args": { + "External id": 1435884,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854070685.761, "dur": 1.115, + "args": { + "External id": 1435885,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2379422, + "ts": 6413854070692.302, "dur": 22.913, + "args": { + "External id": 1435886,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338706, "tid": 2379422, + "ts": 6413854070721.896, "dur": 45.137, + "args": { + "External id": 1435887,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2379422, + "ts": 6413854070723.528, "dur": 43.334, + "args": { + "External id": 1435888,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2379422, + "ts": 6413854070725.190, "dur": 41.280, + "args": { + "External id": 1435889,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854070929.452, "dur": 25.998, + "args": { + "External id": 1435890,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 5873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854070971.939, "dur": 28.676, + "args": { + "External id": 1435891,"Record function id": 0, "Sequence number": 15349101, "Fwd thread id": 1, "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854070973.457, "dur": 23.474, + "args": { + "External id": 1435892,"Sequence number": 15349101, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 5875 + } + }, + { + "ph": "f", "id": 235, "pid": 2338706, "tid": 2379422, "ts": 6413854070973.457, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854070989.425, "dur": 7.259, + "args": { + "External id": 1435893,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854070991.354, "dur": 5.013, + "args": { + "External id": 1435894,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071005.972, "dur": 132.726, + "args": { + "External id": 1435895,"Record function id": 0, "Sequence number": 15349100, "Fwd thread id": 1, "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071007.150, "dur": 122.260, + "args": { + "External id": 1435896,"Sequence number": 15349100, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5879 + } + }, + { + "ph": "f", "id": 236, "pid": 2338706, "tid": 2379422, "ts": 6413854071007.150, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854071010.548, "dur": 118.347, + "args": { + "External id": 1435897,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 5880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854071014.159, "dur": 30.245, + "args": { + "External id": 1435898,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854071020.226, "dur": 4.273, + "args": { + "External id": 1435899,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071025.682, "dur": 18.439, + "args": { + "External id": 1435900,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071027.477, "dur": 16.169, + "args": { + "External id": 1435901,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 5884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854071046.417, "dur": 6.215, + "args": { + "External id": 1435902,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 5885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854071050.935, "dur": 1.223, + "args": { + "External id": 1435903,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071080.385, "dur": 47.230, + "args": { + "External id": 1435904,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071144.869, "dur": 86.777, + "args": { + "External id": 1435905,"Record function id": 0, "Sequence number": 15349099, "Fwd thread id": 1, "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071146.143, "dur": 81.157, + "args": { + "External id": 1435906,"Sequence number": 15349099, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5889 + } + }, + { + "ph": "f", "id": 237, "pid": 2338706, "tid": 2379422, "ts": 6413854071146.143, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854071149.598, "dur": 77.399, + "args": { + "External id": 1435907,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854071152.533, "dur": 25.379, + "args": { + "External id": 1435908,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854071154.885, "dur": 3.307, + "args": { + "External id": 1435909,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071159.227, "dur": 18.419, + "args": { + "External id": 1435910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071163.425, "dur": 13.742, + "args": { + "External id": 1435911,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854071200.399, "dur": 6.780, + "args": { + "External id": 1435912,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 5895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854071205.286, "dur": 1.207, + "args": { + "External id": 1435913,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071207.906, "dur": 18.315, + "args": { + "External id": 1435914,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071236.268, "dur": 148.494, + "args": { + "External id": 1435915,"Record function id": 0, "Sequence number": 15349098, "Fwd thread id": 1, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071237.362, "dur": 142.505, + "args": { + "External id": 1435916,"Sequence number": 15349098, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5899 + } + }, + { + "ph": "f", "id": 238, "pid": 2338706, "tid": 2379422, "ts": 6413854071237.362, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854071240.829, "dur": 138.633, + "args": { + "External id": 1435917,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854071242.713, "dur": 24.401, + "args": { + "External id": 1435918,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854071244.235, "dur": 5.468, + "args": { + "External id": 1435919,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071250.277, "dur": 16.561, + "args": { + "External id": 1435920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071254.288, "dur": 12.117, + "args": { + "External id": 1435921,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854071271.137, "dur": 4.132, + "args": { + "External id": 1435922,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854071274.215, "dur": 0.685, + "args": { + "External id": 1435923,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071276.443, "dur": 102.072, + "args": { + "External id": 1435924,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071392.224, "dur": 122.771, + "args": { + "External id": 1435925,"Record function id": 0, "Sequence number": 15349097, "Fwd thread id": 1, "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071393.422, "dur": 95.247, + "args": { + "External id": 1435926,"Sequence number": 15349097, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5909 + } + }, + { + "ph": "f", "id": 239, "pid": 2338706, "tid": 2379422, "ts": 6413854071393.422, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854071396.049, "dur": 92.315, + "args": { + "External id": 1435927,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854071397.844, "dur": 17.667, + "args": { + "External id": 1435928,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854071399.319, "dur": 2.266, + "args": { + "External id": 1435929,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071402.204, "dur": 13.061, + "args": { + "External id": 1435930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071403.185, "dur": 11.710, + "args": { + "External id": 1435931,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854071419.166, "dur": 3.836, + "args": { + "External id": 1435932,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854071422.245, "dur": 0.563, + "args": { + "External id": 1435933,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071423.913, "dur": 63.471, + "args": { + "External id": 1435934,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071493.997, "dur": 19.585, + "args": { + "External id": 1435935,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071520.011, "dur": 36.489, + "args": { + "External id": 1435936,"Record function id": 0, "Sequence number": 15349096, "Fwd thread id": 1, "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854071521.695, "dur": 1.420, + "args": { + "External id": 1435937,"Sequence number": 15349096, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5920 + } + }, + { + "ph": "f", "id": 240, "pid": 2338706, "tid": 2379422, "ts": 6413854071521.695, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854071526.074, "dur": 26.866, + "args": { + "External id": 1435938,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854071528.958, "dur": 23.547, + "args": { + "External id": 1435939,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854071534.895, "dur": 0.649, + "args": { + "External id": 1435940,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854071561.978, "dur": 3372.159, + "args": { + "External id": 1435941,"Record function id": 0, "Sequence number": 15349094, "Fwd thread id": 1, "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854071563.880, "dur": 3336.697, + "args": { + "External id": 1435942,"Sequence number": 15349094, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5925 + } + }, + { + "ph": "f", "id": 241, "pid": 2338706, "tid": 2379422, "ts": 6413854071563.880, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854071602.891, "dur": 2.695, + "args": { + "External id": 1435943,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854071608.550, "dur": 3069.106, + "args": { + "External id": 1435944,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854071610.438, "dur": 3066.952, + "args": { + "External id": 1435945,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854071614.403, "dur": 6.206, + "args": { + "External id": 1435946,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854071621.483, "dur": 3054.698, + "args": { + "External id": 1435947,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338706, "tid": 2379422, + "ts": 6413854074681.483, "dur": 0.433, + "args": { + "External id": 1435948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854074683.240, "dur": 5.624, + "args": { + "External id": 1435949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854074687.631, "dur": 1.035, + "args": { + "External id": 1435950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2379422, + "ts": 6413854074693.828, "dur": 21.942, + "args": { + "External id": 1435951,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338706, "tid": 2379422, + "ts": 6413854074722.137, "dur": 43.387, + "args": { + "External id": 1435952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2379422, + "ts": 6413854074723.812, "dur": 41.542, + "args": { + "External id": 1435953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2379422, + "ts": 6413854074725.571, "dur": 39.510, + "args": { + "External id": 1435954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854074913.578, "dur": 15.488, + "args": { + "External id": 1435955,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 5938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854074945.046, "dur": 15.091, + "args": { + "External id": 1435956,"Record function id": 0, "Sequence number": 15349093, "Fwd thread id": 1, "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854074946.304, "dur": 10.882, + "args": { + "External id": 1435957,"Sequence number": 15349093, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 5940 + } + }, + { + "ph": "f", "id": 242, "pid": 2338706, "tid": 2379422, "ts": 6413854074946.304, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854074950.293, "dur": 6.658, + "args": { + "External id": 1435958,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854074952.638, "dur": 4.085, + "args": { + "External id": 1435959,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 5942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854074963.638, "dur": 131.762, + "args": { + "External id": 1435960,"Record function id": 0, "Sequence number": 15349092, "Fwd thread id": 1, "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854074964.798, "dur": 122.350, + "args": { + "External id": 1435961,"Sequence number": 15349092, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5944 + } + }, + { + "ph": "f", "id": 243, "pid": 2338706, "tid": 2379422, "ts": 6413854074964.798, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854074968.161, "dur": 118.611, + "args": { + "External id": 1435962,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 5945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854074971.786, "dur": 43.155, + "args": { + "External id": 1435963,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854074989.972, "dur": 4.872, + "args": { + "External id": 1435964,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854074996.516, "dur": 18.108, + "args": { + "External id": 1435965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854074998.671, "dur": 15.442, + "args": { + "External id": 1435966,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 5949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854075016.802, "dur": 7.905, + "args": { + "External id": 1435967,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 5950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854075020.374, "dur": 4.026, + "args": { + "External id": 1435968,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075026.006, "dur": 59.349, + "args": { + "External id": 1435969,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075102.003, "dur": 61.845, + "args": { + "External id": 1435970,"Record function id": 0, "Sequence number": 15349091, "Fwd thread id": 1, "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075103.145, "dur": 56.896, + "args": { + "External id": 1435971,"Sequence number": 15349091, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 5954 + } + }, + { + "ph": "f", "id": 244, "pid": 2338706, "tid": 2379422, "ts": 6413854075103.145, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854075106.745, "dur": 52.974, + "args": { + "External id": 1435972,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854075109.187, "dur": 23.664, + "args": { + "External id": 1435973,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854075110.936, "dur": 3.360, + "args": { + "External id": 1435974,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075118.341, "dur": 14.268, + "args": { + "External id": 1435975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075119.366, "dur": 12.737, + "args": { + "External id": 1435976,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854075134.206, "dur": 7.063, + "args": { + "External id": 1435977,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 5960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854075139.491, "dur": 1.178, + "args": { + "External id": 1435978,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075142.034, "dur": 17.019, + "args": { + "External id": 1435979,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 5962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075167.933, "dur": 125.203, + "args": { + "External id": 1435980,"Record function id": 0, "Sequence number": 15349090, "Fwd thread id": 1, "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075168.984, "dur": 120.027, + "args": { + "External id": 1435981,"Sequence number": 15349090, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5964 + } + }, + { + "ph": "f", "id": 245, "pid": 2338706, "tid": 2379422, "ts": 6413854075168.984, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854075171.625, "dur": 117.092, + "args": { + "External id": 1435982,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854075173.577, "dur": 21.898, + "args": { + "External id": 1435983,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854075174.956, "dur": 2.454, + "args": { + "External id": 1435984,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075178.464, "dur": 16.758, + "args": { + "External id": 1435985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075182.555, "dur": 12.332, + "args": { + "External id": 1435986,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854075196.747, "dur": 4.074, + "args": { + "External id": 1435987,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854075199.858, "dur": 0.702, + "args": { + "External id": 1435988,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075202.236, "dur": 85.595, + "args": { + "External id": 1435989,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075297.648, "dur": 108.292, + "args": { + "External id": 1435990,"Record function id": 0, "Sequence number": 15349089, "Fwd thread id": 1, "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075298.801, "dur": 85.429, + "args": { + "External id": 1435991,"Sequence number": 15349089, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5974 + } + }, + { + "ph": "f", "id": 246, "pid": 2338706, "tid": 2379422, "ts": 6413854075298.801, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854075301.482, "dur": 82.389, + "args": { + "External id": 1435992,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854075303.301, "dur": 19.807, + "args": { + "External id": 1435993,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854075304.776, "dur": 2.243, + "args": { + "External id": 1435994,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075308.069, "dur": 14.773, + "args": { + "External id": 1435995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075311.194, "dur": 11.319, + "args": { + "External id": 1435996,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854075326.809, "dur": 3.400, + "args": { + "External id": 1435997,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854075329.304, "dur": 0.689, + "args": { + "External id": 1435998,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075331.149, "dur": 51.805, + "args": { + "External id": 1435999,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075389.136, "dur": 15.509, + "args": { + "External id": 1436000,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 5983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075411.010, "dur": 41.849, + "args": { + "External id": 1436001,"Record function id": 0, "Sequence number": 15349088, "Fwd thread id": 1, "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854075412.764, "dur": 1.366, + "args": { + "External id": 1436002,"Sequence number": 15349088, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 5985 + } + }, + { + "ph": "f", "id": 247, "pid": 2338706, "tid": 2379422, "ts": 6413854075412.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854075416.569, "dur": 31.161, + "args": { + "External id": 1436003,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854075418.652, "dur": 28.628, + "args": { + "External id": 1436004,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854075424.928, "dur": 3.736, + "args": { + "External id": 1436005,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 5988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854075457.936, "dur": 3451.440, + "args": { + "External id": 1436006,"Record function id": 0, "Sequence number": 15349087, "Fwd thread id": 1, "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854075472.007, "dur": 3401.294, + "args": { + "External id": 1436007,"Sequence number": 15349087, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5990 + } + }, + { + "ph": "f", "id": 248, "pid": 2338706, "tid": 2379422, "ts": 6413854075472.007, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854075504.555, "dur": 2.756, + "args": { + "External id": 1436008,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854075509.785, "dur": 3154.292, + "args": { + "External id": 1436009,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854075511.731, "dur": 3152.059, + "args": { + "External id": 1436010,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854075515.497, "dur": 4.429, + "args": { + "External id": 1436011,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854075521.016, "dur": 3141.819, + "args": { + "External id": 1436012,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 2338706, "tid": 2379422, + "ts": 6413854078667.610, "dur": 0.432, + "args": { + "External id": 1436013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854078672.626, "dur": 2.630, + "args": { + "External id": 1436014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338706, "tid": 2379422, + "ts": 6413854078674.284, "dur": 0.852, + "args": { + "External id": 1436015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2379422, + "ts": 6413854078679.870, "dur": 21.771, + "args": { + "External id": 1436016,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 5999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338706, "tid": 2379422, + "ts": 6413854078707.217, "dur": 40.915, + "args": { + "External id": 1436017,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2379422, + "ts": 6413854078708.547, "dur": 39.419, + "args": { + "External id": 1436018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2379422, + "ts": 6413854078709.975, "dur": 37.780, + "args": { + "External id": 1436019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 6002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854078886.713, "dur": 17.331, + "args": { + "External id": 1436020,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 6003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854078925.045, "dur": 16.251, + "args": { + "External id": 1436021,"Record function id": 0, "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854078927.872, "dur": 11.294, + "args": { + "External id": 1436022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 6005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854078932.471, "dur": 4.917, + "args": { + "External id": 1436023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 6006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854078933.546, "dur": 3.728, + "args": { + "External id": 1436024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 6007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854078944.901, "dur": 17.039, + "args": { + "External id": 1436025,"Record function id": 0, "Sequence number": 15349086, "Fwd thread id": 1, "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854078946.195, "dur": 11.776, + "args": { + "External id": 1436026,"Sequence number": 15349086, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6009 + } + }, + { + "ph": "f", "id": 249, "pid": 2338706, "tid": 2379422, "ts": 6413854078946.195, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854078949.941, "dur": 7.758, + "args": { + "External id": 1436027,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854078954.346, "dur": 3.175, + "args": { + "External id": 1436028,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854078965.525, "dur": 132.318, + "args": { + "External id": 1436029,"Record function id": 0, "Sequence number": 15349085, "Fwd thread id": 1, "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854078966.597, "dur": 122.920, + "args": { + "External id": 1436030,"Sequence number": 15349085, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6013 + } + }, + { + "ph": "f", "id": 250, "pid": 2338706, "tid": 2379422, "ts": 6413854078966.597, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854078969.615, "dur": 119.487, + "args": { + "External id": 1436031,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854078972.956, "dur": 43.679, + "args": { + "External id": 1436032,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854078975.089, "dur": 16.749, + "args": { + "External id": 1436033,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854078993.705, "dur": 22.664, + "args": { + "External id": 1436034,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854078995.220, "dur": 20.553, + "args": { + "External id": 1436035,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854079018.369, "dur": 5.968, + "args": { + "External id": 1436036,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 6019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079022.238, "dur": 1.717, + "args": { + "External id": 1436037,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[16777216, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079028.715, "dur": 59.269, + "args": { + "External id": 1436038,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079104.775, "dur": 64.852, + "args": { + "External id": 1436039,"Record function id": 0, "Sequence number": 15349084, "Fwd thread id": 1, "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079105.917, "dur": 59.880, + "args": { + "External id": 1436040,"Sequence number": 15349084, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6023 + } + }, + { + "ph": "f", "id": 251, "pid": 2338706, "tid": 2379422, "ts": 6413854079105.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079109.642, "dur": 55.866, + "args": { + "External id": 1436041,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 6024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854079112.606, "dur": 24.163, + "args": { + "External id": 1436042,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854079114.638, "dur": 6.334, + "args": { + "External id": 1436043,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079121.656, "dur": 14.833, + "args": { + "External id": 1436044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079122.876, "dur": 13.201, + "args": { + "External id": 1436045,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 6028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854079138.446, "dur": 8.685, + "args": { + "External id": 1436046,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079145.533, "dur": 0.950, + "args": { + "External id": 1436047,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079148.153, "dur": 16.824, + "args": { + "External id": 1436048,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079173.466, "dur": 130.611, + "args": { + "External id": 1436049,"Record function id": 0, "Sequence number": 15349083, "Fwd thread id": 1, "Ev Idx": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079175.068, "dur": 125.177, + "args": { + "External id": 1436050,"Sequence number": 15349083, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6033 + } + }, + { + "ph": "f", "id": 252, "pid": 2338706, "tid": 2379422, "ts": 6413854079175.068, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079177.990, "dur": 121.849, + "args": { + "External id": 1436051,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854079179.744, "dur": 25.657, + "args": { + "External id": 1436052,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854079181.224, "dur": 2.113, + "args": { + "External id": 1436053,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079189.413, "dur": 15.724, + "args": { + "External id": 1436054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079192.536, "dur": 12.253, + "args": { + "External id": 1436055,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 6038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854079209.169, "dur": 3.616, + "args": { + "External id": 1436056,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 6039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079211.780, "dur": 0.730, + "args": { + "External id": 1436057,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079214.017, "dur": 85.091, + "args": { + "External id": 1436058,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079310.878, "dur": 108.857, + "args": { + "External id": 1436059,"Record function id": 0, "Sequence number": 15349082, "Fwd thread id": 1, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079312.191, "dur": 85.168, + "args": { + "External id": 1436060,"Sequence number": 15349082, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6043 + } + }, + { + "ph": "f", "id": 253, "pid": 2338706, "tid": 2379422, "ts": 6413854079312.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079315.486, "dur": 81.564, + "args": { + "External id": 1436061,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], [], []], "Ev Idx": 6044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2379422, + "ts": 6413854079317.038, "dur": 18.313, + "args": { + "External id": 1436062,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 6045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854079318.440, "dur": 2.132, + "args": { + "External id": 1436063,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4, 4096]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079321.344, "dur": 13.722, + "args": { + "External id": 1436064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079322.554, "dur": 12.172, + "args": { + "External id": 1436065,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], []], "Ev Idx": 6048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854079339.727, "dur": 3.671, + "args": { + "External id": 1436066,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 6049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079342.569, "dur": 0.584, + "args": { + "External id": 1436067,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079344.389, "dur": 51.915, + "args": { + "External id": 1436068,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 6051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854079402.849, "dur": 14.977, + "args": { + "External id": 1436069,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [67108864, 16384, 4096, 1], []], "Input Dims": [[8, 4096, 4, 4096], [8, 4096, 4, 4096], []], "Ev Idx": 6052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079427.553, "dur": 406.547, + "args": { + "External id": 1436070,"Record function id": 0, "Sequence number": 15349081, "Fwd thread id": 1, "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079429.643, "dur": 394.006, + "args": { + "External id": 1436071,"Sequence number": 15349081, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6054 + } + }, + { + "ph": "f", "id": 254, "pid": 2338706, "tid": 2379422, "ts": 6413854079429.643, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079638.331, "dur": 48.977, + "args": { + "External id": 1436072,"kernel_hash": "cxv3u4whmia24aefmfuiol55m7osx2elddgy6rxbkbvmnigizet6", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "131072", "4096", "1", "993", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xv/cxv3u4whmia24aefmfuiol55m7osx2elddgy6rxbkbvmnigizet6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [4096], [131072, 4096], [131072, 4096], [132, 4096], [131072], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079726.324, "dur": 29.468, + "args": { + "External id": 1436073,"kernel_hash": "chd4lphpu733jd27rokzqqzh23vkeai2aitqgvmlc7xjqod3vr6m", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/hd/chd4lphpu733jd27rokzqqzh23vkeai2aitqgvmlc7xjqod3vr6m.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854079775.422, "dur": 22.096, + "args": { + "External id": 1436074,"kernel_hash": "cginwarxhlqgizmvepo2jober6dgvr4lj6cd6nlltcu72kqzvxpx", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/gi/cginwarxhlqgizmvepo2jober6dgvr4lj6cd6nlltcu72kqzvxpx.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854079842.781, "dur": 12.207, + "args": { + "External id": 1436075,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854079845.018, "dur": 9.111, + "args": { + "External id": 1436076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854079848.149, "dur": 4.949, + "args": { + "External id": 1436077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854079849.603, "dur": 3.389, + "args": { + "External id": 1436078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079859.138, "dur": 44.495, + "args": { + "External id": 1436079,"Record function id": 0, "Sequence number": 15349080, "Fwd thread id": 1, "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079860.107, "dur": 31.845, + "args": { + "External id": 1436080,"Sequence number": 15349080, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 4096, 1]], "Input Dims": [[8, 4096, 4, 4096]], "Ev Idx": 6063 + } + }, + { + "ph": "f", "id": 255, "pid": 2338706, "tid": 2379422, "ts": 6413854079860.107, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854079862.541, "dur": 8.866, + "args": { + "External id": 1436081,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079868.550, "dur": 0.992, + "args": { + "External id": 1436082,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854079871.994, "dur": 5.096, + "args": { + "External id": 1436083,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079874.998, "dur": 0.622, + "args": { + "External id": 1436084,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854079877.589, "dur": 6.462, + "args": { + "External id": 1436085,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079882.474, "dur": 0.589, + "args": { + "External id": 1436086,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2379422, + "ts": 6413854079884.750, "dur": 6.669, + "args": { + "External id": 1436087,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 6070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854079887.479, "dur": 3.044, + "args": { + "External id": 1436088,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 6071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079907.612, "dur": 9.306, + "args": { + "External id": 1436089,"Record function id": 0, "Sequence number": 15349079, "Fwd thread id": 1, "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854079908.678, "dur": 1.444, + "args": { + "External id": 1436090,"Sequence number": 15349079, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6073 + } + }, + { + "ph": "f", "id": 256, "pid": 2338706, "tid": 2379422, "ts": 6413854079908.678, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079922.370, "dur": 716.589, + "args": { + "External id": 1436091,"Record function id": 0, "Sequence number": 15349078, "Fwd thread id": 1, "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854079924.092, "dur": 695.200, + "args": { + "External id": 1436092,"Sequence number": 15349078, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6075 + } + }, + { + "ph": "f", "id": 257, "pid": 2338706, "tid": 2379422, "ts": 6413854079924.092, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854079992.712, "dur": 18.149, + "args": { + "External id": 1436093,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854080001.719, "dur": 8.635, + "args": { + "External id": 1436094,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 6077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854080018.638, "dur": 9.385, + "args": { + "External id": 1436095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854080022.663, "dur": 4.198, + "args": { + "External id": 1436096,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080025.317, "dur": 1.303, + "args": { + "External id": 1436097,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413854080034.290, "dur": 212.683, + "args": { + "External id": 1436098,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 6081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854080038.272, "dur": 3.915, + "args": { + "External id": 1436099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 6082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854080038.907, "dur": 2.311, + "args": { + "External id": 1436100,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080040.514, "dur": 0.602, + "args": { + "External id": 1436101,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413854080093.137, "dur": 152.970, + "args": { + "External id": 1436102,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854080097.215, "dur": 147.791, + "args": { + "External id": 1436103,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854080256.407, "dur": 7.058, + "args": { + "External id": 1436104,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 6087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080260.026, "dur": 3.266, + "args": { + "External id": 1436105,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854080315.928, "dur": 8.209, + "args": { + "External id": 1436106,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854080326.041, "dur": 2.020, + "args": { + "External id": 1436107,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854080329.814, "dur": 7.666, + "args": { + "External id": 1436108,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854080379.651, "dur": 4.806, + "args": { + "External id": 1436109,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080380.563, "dur": 3.707, + "args": { + "External id": 1436110,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413854080421.459, "dur": 169.982, + "args": { + "External id": 1436111,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 6094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854080429.717, "dur": 9.605, + "args": { + "External id": 1436112,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080436.772, "dur": 1.164, + "args": { + "External id": 1436113,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854080442.341, "dur": 7.510, + "args": { + "External id": 1436114,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 6097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080447.769, "dur": 0.664, + "args": { + "External id": 1436115,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 6098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854080451.844, "dur": 3.939, + "args": { + "External id": 1436116,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080454.604, "dur": 0.797, + "args": { + "External id": 1436117,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854080456.582, "dur": 3.861, + "args": { + "External id": 1436118,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080458.813, "dur": 0.560, + "args": { + "External id": 1436119,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 6102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854080466.900, "dur": 5.659, + "args": { + "External id": 1436120,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 6103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080471.512, "dur": 0.701, + "args": { + "External id": 1436121,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 6104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854080473.886, "dur": 7.545, + "args": { + "External id": 1436122,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 6105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854080479.148, "dur": 2.055, + "args": { + "External id": 1436123,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 6106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854080485.183, "dur": 5.699, + "args": { + "External id": 1436124,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 6107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080487.514, "dur": 3.064, + "args": { + "External id": 1436125,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 6108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854080491.692, "dur": 3.383, + "args": { + "External id": 1436126,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080492.892, "dur": 2.085, + "args": { + "External id": 1436127,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854080496.995, "dur": 79.830, + "args": { + "External id": 1436128,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 6111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080579.047, "dur": 1.186, + "args": { + "External id": 1436129,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 6112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854080581.222, "dur": 4.781, + "args": { + "External id": 1436130,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080584.264, "dur": 0.788, + "args": { + "External id": 1436131,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080588.503, "dur": 1.157, + "args": { + "External id": 1436132,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 6115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854080653.302, "dur": 12.029, + "args": { + "External id": 1436133,"Record function id": 0, "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854080656.013, "dur": 8.435, + "args": { + "External id": 1436134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854080658.962, "dur": 4.587, + "args": { + "External id": 1436135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854080660.383, "dur": 3.064, + "args": { + "External id": 1436136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080669.346, "dur": 10.859, + "args": { + "External id": 1436137,"Record function id": 0, "Sequence number": 15349077, "Fwd thread id": 1, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080671.148, "dur": 5.089, + "args": { + "External id": 1436138,"Sequence number": 15349077, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6121 + } + }, + { + "ph": "f", "id": 258, "pid": 2338706, "tid": 2379422, "ts": 6413854080671.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854080673.278, "dur": 2.673, + "args": { + "External id": 1436139,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080674.626, "dur": 1.179, + "args": { + "External id": 1436140,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080684.295, "dur": 146.815, + "args": { + "External id": 1436141,"Record function id": 0, "Sequence number": 15349076, "Fwd thread id": 1, "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080685.599, "dur": 135.687, + "args": { + "External id": 1436142,"Sequence number": 15349076, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6125 + } + }, + { + "ph": "f", "id": 259, "pid": 2338706, "tid": 2379422, "ts": 6413854080685.599, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854080691.774, "dur": 7.216, + "args": { + "External id": 1436143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854080693.368, "dur": 4.980, + "args": { + "External id": 1436144,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080697.675, "dur": 0.494, + "args": { + "External id": 1436145,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854080700.413, "dur": 55.085, + "args": { + "External id": 1436146,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854080757.084, "dur": 4.715, + "args": { + "External id": 1436147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854080757.863, "dur": 3.311, + "args": { + "External id": 1436148,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080760.030, "dur": 0.967, + "args": { + "External id": 1436149,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854080764.151, "dur": 6.234, + "args": { + "External id": 1436150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854080765.413, "dur": 4.509, + "args": { + "External id": 1436151,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080769.428, "dur": 0.414, + "args": { + "External id": 1436152,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854080771.144, "dur": 49.376, + "args": { + "External id": 1436153,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080835.964, "dur": 9.734, + "args": { + "External id": 1436154,"Record function id": 0, "Sequence number": 15349075, "Fwd thread id": 1, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080837.024, "dur": 5.768, + "args": { + "External id": 1436155,"Sequence number": 15349075, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6138 + } + }, + { + "ph": "f", "id": 260, "pid": 2338706, "tid": 2379422, "ts": 6413854080837.024, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854080839.739, "dur": 2.905, + "args": { + "External id": 1436156,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080841.291, "dur": 1.142, + "args": { + "External id": 1436157,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080849.991, "dur": 111.343, + "args": { + "External id": 1436158,"Record function id": 0, "Sequence number": 15349074, "Fwd thread id": 1, "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080851.090, "dur": 106.403, + "args": { + "External id": 1436159,"Sequence number": 15349074, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6142 + } + }, + { + "ph": "f", "id": 261, "pid": 2338706, "tid": 2379422, "ts": 6413854080851.090, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854080852.208, "dur": 105.042, + "args": { + "External id": 1436160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854080937.207, "dur": 19.161, + "args": { + "External id": 1440769,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854080955.453, "dur": 0.733, + "args": { + "External id": 1440770,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854080966.003, "dur": 5.400, + "args": { + "External id": 1440771,"Record function id": 0, "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854080967.686, "dur": 3.156, + "args": { + "External id": 1440772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854080968.665, "dur": 1.925, + "args": { + "External id": 1440773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854080969.233, "dur": 1.265, + "args": { + "External id": 1440774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080974.495, "dur": 29.058, + "args": { + "External id": 1440775,"Record function id": 0, "Sequence number": 15349073, "Fwd thread id": 1, "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854080976.040, "dur": 22.424, + "args": { + "External id": 1440776,"Sequence number": 15349073, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6151 + } + }, + { + "ph": "f", "id": 262, "pid": 2338706, "tid": 2379422, "ts": 6413854080976.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854080995.960, "dur": 2.326, + "args": { + "External id": 1440777,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854080996.657, "dur": 1.374, + "args": { + "External id": 1440778,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081008.741, "dur": 163.343, + "args": { + "External id": 1440779,"Record function id": 0, "Sequence number": 15349072, "Fwd thread id": 1, "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081011.848, "dur": 147.000, + "args": { + "External id": 1440780,"Sequence number": 15349072, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6155 + } + }, + { + "ph": "f", "id": 263, "pid": 2338706, "tid": 2379422, "ts": 6413854081011.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081015.209, "dur": 3.075, + "args": { + "External id": 1440781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081015.985, "dur": 1.823, + "args": { + "External id": 1440782,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081017.200, "dur": 0.513, + "args": { + "External id": 1440783,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854081019.122, "dur": 82.325, + "args": { + "External id": 1440784,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081103.888, "dur": 8.152, + "args": { + "External id": 1440785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081105.197, "dur": 6.023, + "args": { + "External id": 1440786,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081110.178, "dur": 0.897, + "args": { + "External id": 1440787,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081113.702, "dur": 5.802, + "args": { + "External id": 1440788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081114.754, "dur": 4.080, + "args": { + "External id": 1440789,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081116.287, "dur": 2.468, + "args": { + "External id": 1440790,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854081120.102, "dur": 37.925, + "args": { + "External id": 1440791,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081181.243, "dur": 42.665, + "args": { + "External id": 1440792,"Record function id": 0, "Sequence number": 15349071, "Fwd thread id": 1, "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081182.264, "dur": 7.604, + "args": { + "External id": 1440793,"Sequence number": 15349071, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6168 + } + }, + { + "ph": "f", "id": 264, "pid": 2338706, "tid": 2379422, "ts": 6413854081182.264, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081184.493, "dur": 5.216, + "args": { + "External id": 1440794,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081185.763, "dur": 3.773, + "args": { + "External id": 1440795,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854081194.543, "dur": 26.025, + "args": { + "External id": 1440796,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081228.586, "dur": 12.455, + "args": { + "External id": 1440797,"Record function id": 0, "Sequence number": 15349070, "Fwd thread id": 1, "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081229.553, "dur": 8.118, + "args": { + "External id": 1440798,"Sequence number": 15349070, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6173 + } + }, + { + "ph": "f", "id": 265, "pid": 2338706, "tid": 2379422, "ts": 6413854081229.553, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081233.534, "dur": 3.930, + "args": { + "External id": 1440799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081234.477, "dur": 2.383, + "args": { + "External id": 1440800,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081236.148, "dur": 0.563, + "args": { + "External id": 1440801,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854081245.949, "dur": 5.931, + "args": { + "External id": 1440802,"Record function id": 0, "Ev Idx": 6177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854081247.649, "dur": 3.719, + "args": { + "External id": 1440803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854081248.726, "dur": 2.177, + "args": { + "External id": 1440804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854081249.315, "dur": 1.479, + "args": { + "External id": 1440805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854081257.140, "dur": 497.019, + "args": { + "External id": 1440806,"Record function id": 0, "Sequence number": 15349069, "Fwd thread id": 1, "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854081258.527, "dur": 478.087, + "args": { + "External id": 1440807,"Sequence number": 15349069, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 6182 + } + }, + { + "ph": "f", "id": 266, "pid": 2338706, "tid": 2379422, "ts": 6413854081258.527, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413854081292.727, "dur": 40.191, + "args": { + "External id": 1440808,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854081295.134, "dur": 37.587, + "args": { + "External id": 1440809,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854081299.469, "dur": 7.202, + "args": { + "External id": 1440810,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854081302.477, "dur": 3.494, + "args": { + "External id": 1440811,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854081308.197, "dur": 24.089, + "args": { + "External id": 1440812,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081348.828, "dur": 5.155, + "args": { + "External id": 1440813,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081352.739, "dur": 1.095, + "args": { + "External id": 1440814,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081358.014, "dur": 2.166, + "args": { + "External id": 1440815,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081359.304, "dur": 0.779, + "args": { + "External id": 1440816,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854081377.718, "dur": 4.713, + "args": { + "External id": 1440817,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854081398.243, "dur": 2.863, + "args": { + "External id": 1440818,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081608.676, "dur": 2.720, + "args": { + "External id": 1440819,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854081616.973, "dur": 39.946, + "args": { + "External id": 1440820,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081630.472, "dur": 0.982, + "args": { + "External id": 1440821,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854081663.889, "dur": 33.106, + "args": { + "External id": 1440822,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854081665.771, "dur": 31.014, + "args": { + "External id": 1440823,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081670.616, "dur": 4.564, + "args": { + "External id": 1440824,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854081676.832, "dur": 19.399, + "args": { + "External id": 1440825,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854081704.804, "dur": 3.142, + "args": { + "External id": 1440826,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081706.416, "dur": 1.382, + "args": { + "External id": 1440827,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081718.566, "dur": 3.434, + "args": { + "External id": 1440828,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081720.531, "dur": 1.364, + "args": { + "External id": 1440829,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081724.539, "dur": 2.537, + "args": { + "External id": 1440830,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081725.940, "dur": 1.054, + "args": { + "External id": 1440831,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854081764.901, "dur": 12.951, + "args": { + "External id": 1440832,"Record function id": 0, "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854081767.229, "dur": 9.946, + "args": { + "External id": 1440833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854081769.131, "dur": 7.172, + "args": { + "External id": 1440834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854081772.488, "dur": 3.635, + "args": { + "External id": 1440835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081781.509, "dur": 10.320, + "args": { + "External id": 1440836,"Record function id": 0, "Sequence number": 15349068, "Fwd thread id": 1, "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081783.056, "dur": 4.977, + "args": { + "External id": 1440837,"Sequence number": 15349068, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6212 + } + }, + { + "ph": "f", "id": 267, "pid": 2338706, "tid": 2379422, "ts": 6413854081783.056, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081785.070, "dur": 2.764, + "args": { + "External id": 1440838,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081786.519, "dur": 1.171, + "args": { + "External id": 1440839,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081795.360, "dur": 155.121, + "args": { + "External id": 1440840,"Record function id": 0, "Sequence number": 15349067, "Fwd thread id": 1, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081796.430, "dur": 147.378, + "args": { + "External id": 1440841,"Sequence number": 15349067, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6216 + } + }, + { + "ph": "f", "id": 268, "pid": 2338706, "tid": 2379422, "ts": 6413854081796.430, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081802.154, "dur": 7.990, + "args": { + "External id": 1440842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081803.877, "dur": 5.699, + "args": { + "External id": 1440843,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081808.800, "dur": 0.623, + "args": { + "External id": 1440844,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854081811.425, "dur": 71.100, + "args": { + "External id": 1440845,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081883.821, "dur": 4.584, + "args": { + "External id": 1440846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081884.928, "dur": 2.773, + "args": { + "External id": 1440847,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081886.869, "dur": 0.694, + "args": { + "External id": 1440848,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081890.361, "dur": 8.723, + "args": { + "External id": 1440849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081891.328, "dur": 7.287, + "args": { + "External id": 1440850,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081895.605, "dur": 2.914, + "args": { + "External id": 1440851,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854081899.734, "dur": 43.204, + "args": { + "External id": 1440852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081955.738, "dur": 8.678, + "args": { + "External id": 1440853,"Record function id": 0, "Sequence number": 15349066, "Fwd thread id": 1, "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081956.671, "dur": 4.751, + "args": { + "External id": 1440854,"Sequence number": 15349066, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6229 + } + }, + { + "ph": "f", "id": 269, "pid": 2338706, "tid": 2379422, "ts": 6413854081956.671, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854081958.872, "dur": 2.413, + "args": { + "External id": 1440855,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854081960.085, "dur": 1.062, + "args": { + "External id": 1440856,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081968.367, "dur": 32.429, + "args": { + "External id": 1440857,"Record function id": 0, "Sequence number": 15349065, "Fwd thread id": 1, "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854081969.394, "dur": 27.297, + "args": { + "External id": 1440858,"Sequence number": 15349065, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6233 + } + }, + { + "ph": "f", "id": 270, "pid": 2338706, "tid": 2379422, "ts": 6413854081969.394, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854081970.499, "dur": 25.650, + "args": { + "External id": 1440859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854081971.315, "dur": 5.021, + "args": { + "External id": 1440860,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854081975.389, "dur": 0.807, + "args": { + "External id": 1440861,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854082007.541, "dur": 7.520, + "args": { + "External id": 1440862,"Record function id": 0, "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854082009.056, "dur": 5.502, + "args": { + "External id": 1440863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854082011.350, "dur": 2.939, + "args": { + "External id": 1440864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854082012.262, "dur": 1.933, + "args": { + "External id": 1440865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854082018.373, "dur": 8.736, + "args": { + "External id": 1440866,"Record function id": 0, "Sequence number": 15349064, "Fwd thread id": 1, "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854082019.443, "dur": 5.193, + "args": { + "External id": 1440867,"Sequence number": 15349064, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6242 + } + }, + { + "ph": "f", "id": 271, "pid": 2338706, "tid": 2379422, "ts": 6413854082019.443, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854082021.779, "dur": 2.724, + "args": { + "External id": 1440868,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854082022.825, "dur": 1.534, + "args": { + "External id": 1440869,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082032.434, "dur": 541.068, + "args": { + "External id": 1440870,"Record function id": 0, "Sequence number": 15349063, "Fwd thread id": 1, "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082033.642, "dur": 512.925, + "args": { + "External id": 1440871,"Sequence number": 15349063, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6246 + } + }, + { + "ph": "f", "id": 272, "pid": 2338706, "tid": 2379422, "ts": 6413854082033.642, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854082093.494, "dur": 10.844, + "args": { + "External id": 1440872,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082097.523, "dur": 6.092, + "args": { + "External id": 1440873,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854082107.113, "dur": 4.594, + "args": { + "External id": 1440874,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082108.889, "dur": 2.543, + "args": { + "External id": 1440875,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854082113.419, "dur": 7.751, + "args": { + "External id": 1440876,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082115.621, "dur": 5.319, + "args": { + "External id": 1440877,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082192.929, "dur": 324.034, + "args": { + "External id": 1440878,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 6253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854082323.931, "dur": 3.794, + "args": { + "External id": 1440879,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854082330.093, "dur": 2.499, + "args": { + "External id": 1440880,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854082334.128, "dur": 1.960, + "args": { + "External id": 1440881,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854082337.738, "dur": 2.365, + "args": { + "External id": 1440882,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854082399.848, "dur": 6.106, + "args": { + "External id": 1440883,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854082401.526, "dur": 4.246, + "args": { + "External id": 1440884,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854082411.034, "dur": 34.632, + "args": { + "External id": 1440885,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082419.426, "dur": 1.344, + "args": { + "External id": 1440886,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854082447.213, "dur": 1.440, + "args": { + "External id": 1440887,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854082448.015, "dur": 0.571, + "args": { + "External id": 1440888,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854082450.213, "dur": 16.271, + "args": { + "External id": 1440889,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082452.267, "dur": 0.761, + "args": { + "External id": 1440890,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854082532.615, "dur": 4.731, + "args": { + "External id": 1440891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854082540.144, "dur": 0.576, + "args": { + "External id": 1440892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854082542.737, "dur": 0.673, + "args": { + "External id": 1440893,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082584.924, "dur": 267.053, + "args": { + "External id": 1440894,"Record function id": 0, "Sequence number": 15349062, "Fwd thread id": 1, "Ev Idx": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082586.786, "dur": 257.633, + "args": { + "External id": 1440895,"Sequence number": 15349062, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6270 + } + }, + { + "ph": "f", "id": 273, "pid": 2338706, "tid": 2379422, "ts": 6413854082586.786, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854082612.971, "dur": 53.797, + "args": { + "External id": 1440896,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082617.033, "dur": 3.161, + "args": { + "External id": 1440897,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854082621.813, "dur": 44.299, + "args": { + "External id": 1440898,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 6273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854082678.129, "dur": 5.226, + "args": { + "External id": 1440899,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082680.933, "dur": 2.151, + "args": { + "External id": 1440900,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082859.704, "dur": 249.897, + "args": { + "External id": 1440901,"Record function id": 0, "Sequence number": 15349061, "Fwd thread id": 1, "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854082861.525, "dur": 238.004, + "args": { + "External id": 1440902,"Sequence number": 15349061, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6277 + } + }, + { + "ph": "f", "id": 274, "pid": 2338706, "tid": 2379422, "ts": 6413854082861.525, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854082874.354, "dur": 52.767, + "args": { + "External id": 1440903,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082877.743, "dur": 3.149, + "args": { + "External id": 1440904,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854082881.963, "dur": 44.682, + "args": { + "External id": 1440905,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 6280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854082934.894, "dur": 6.031, + "args": { + "External id": 1440906,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854082937.638, "dur": 3.005, + "args": { + "External id": 1440907,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083119.645, "dur": 16.434, + "args": { + "External id": 1440908,"Record function id": 0, "Sequence number": 15349060, "Fwd thread id": 1, "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083121.657, "dur": 10.887, + "args": { + "External id": 1440909,"Sequence number": 15349060, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6284 + } + }, + { + "ph": "f", "id": 275, "pid": 2338706, "tid": 2379422, "ts": 6413854083121.657, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083124.737, "dur": 7.549, + "args": { + "External id": 1440910,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083126.548, "dur": 5.471, + "args": { + "External id": 1440911,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083139.618, "dur": 8.371, + "args": { + "External id": 1440912,"Record function id": 0, "Sequence number": 15349059, "Fwd thread id": 1, "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083140.812, "dur": 4.155, + "args": { + "External id": 1440913,"Sequence number": 15349059, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6288 + } + }, + { + "ph": "f", "id": 276, "pid": 2338706, "tid": 2379422, "ts": 6413854083140.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083142.582, "dur": 2.227, + "args": { + "External id": 1440914,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083143.765, "dur": 0.915, + "args": { + "External id": 1440915,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083150.956, "dur": 28.067, + "args": { + "External id": 1440916,"Record function id": 0, "Sequence number": 15349058, "Fwd thread id": 1, "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083165.641, "dur": 9.816, + "args": { + "External id": 1440917,"Sequence number": 15349058, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6292 + } + }, + { + "ph": "f", "id": 277, "pid": 2338706, "tid": 2379422, "ts": 6413854083165.641, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083170.236, "dur": 5.075, + "args": { + "External id": 1440918,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083171.532, "dur": 3.632, + "args": { + "External id": 1440919,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083183.143, "dur": 8.065, + "args": { + "External id": 1440920,"Record function id": 0, "Sequence number": 15349057, "Fwd thread id": 1, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083184.453, "dur": 4.090, + "args": { + "External id": 1440921,"Sequence number": 15349057, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6296 + } + }, + { + "ph": "f", "id": 278, "pid": 2338706, "tid": 2379422, "ts": 6413854083184.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083185.678, "dur": 2.713, + "args": { + "External id": 1440922,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083186.619, "dur": 1.684, + "args": { + "External id": 1440923,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083194.733, "dur": 174.599, + "args": { + "External id": 1440924,"Record function id": 0, "Sequence number": 15349056, "Fwd thread id": 1, "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083196.238, "dur": 165.466, + "args": { + "External id": 1440925,"Sequence number": 15349056, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6300 + } + }, + { + "ph": "f", "id": 279, "pid": 2338706, "tid": 2379422, "ts": 6413854083196.238, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083201.702, "dur": 11.013, + "args": { + "External id": 1440926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083207.144, "dur": 4.900, + "args": { + "External id": 1440927,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083209.986, "dur": 1.780, + "args": { + "External id": 1440928,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854083214.654, "dur": 80.219, + "args": { + "External id": 1440929,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083296.403, "dur": 7.537, + "args": { + "External id": 1440930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083297.034, "dur": 5.973, + "args": { + "External id": 1440931,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083299.618, "dur": 3.159, + "args": { + "External id": 1440932,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083308.769, "dur": 3.921, + "args": { + "External id": 1440933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083310.097, "dur": 2.077, + "args": { + "External id": 1440934,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083311.562, "dur": 0.552, + "args": { + "External id": 1440935,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854083313.280, "dur": 47.611, + "args": { + "External id": 1440936,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083374.518, "dur": 8.249, + "args": { + "External id": 1440937,"Record function id": 0, "Sequence number": 15349055, "Fwd thread id": 1, "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083375.596, "dur": 4.885, + "args": { + "External id": 1440938,"Sequence number": 15349055, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6313 + } + }, + { + "ph": "f", "id": 280, "pid": 2338706, "tid": 2379422, "ts": 6413854083375.596, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083377.837, "dur": 2.504, + "args": { + "External id": 1440939,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083378.965, "dur": 1.273, + "args": { + "External id": 1440940,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083386.388, "dur": 13.977, + "args": { + "External id": 1440941,"Record function id": 0, "Sequence number": 15349054, "Fwd thread id": 1, "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083387.361, "dur": 10.217, + "args": { + "External id": 1440942,"Sequence number": 15349054, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6317 + } + }, + { + "ph": "f", "id": 281, "pid": 2338706, "tid": 2379422, "ts": 6413854083387.361, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083391.421, "dur": 5.955, + "args": { + "External id": 1440943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083392.310, "dur": 4.575, + "args": { + "External id": 1440944,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083394.127, "dur": 2.669, + "args": { + "External id": 1440945,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854083406.581, "dur": 9.767, + "args": { + "External id": 1440946,"Record function id": 0, "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854083408.292, "dur": 7.189, + "args": { + "External id": 1440947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854083411.171, "dur": 3.856, + "args": { + "External id": 1440948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854083412.516, "dur": 2.418, + "args": { + "External id": 1440949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083419.694, "dur": 7.953, + "args": { + "External id": 1440950,"Record function id": 0, "Sequence number": 15349053, "Fwd thread id": 1, "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083421.051, "dur": 3.843, + "args": { + "External id": 1440951,"Sequence number": 15349053, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6326 + } + }, + { + "ph": "f", "id": 282, "pid": 2338706, "tid": 2379422, "ts": 6413854083421.051, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083422.994, "dur": 1.747, + "args": { + "External id": 1440952,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083423.953, "dur": 0.698, + "args": { + "External id": 1440953,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083433.164, "dur": 97.421, + "args": { + "External id": 1440954,"Record function id": 0, "Sequence number": 15349052, "Fwd thread id": 1, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083435.979, "dur": 86.930, + "args": { + "External id": 1440955,"Sequence number": 15349052, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6330 + } + }, + { + "ph": "f", "id": 283, "pid": 2338706, "tid": 2379422, "ts": 6413854083435.979, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083439.905, "dur": 3.349, + "args": { + "External id": 1440956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083440.715, "dur": 2.026, + "args": { + "External id": 1440957,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083442.204, "dur": 0.431, + "args": { + "External id": 1440958,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854083444.323, "dur": 26.492, + "args": { + "External id": 1440959,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083471.664, "dur": 11.264, + "args": { + "External id": 1440960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083472.506, "dur": 9.825, + "args": { + "External id": 1440961,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083479.414, "dur": 2.787, + "args": { + "External id": 1440962,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083484.382, "dur": 3.667, + "args": { + "External id": 1440963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083485.191, "dur": 2.130, + "args": { + "External id": 1440964,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083486.774, "dur": 0.482, + "args": { + "External id": 1440965,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854083488.422, "dur": 33.774, + "args": { + "External id": 1440966,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083535.400, "dur": 37.447, + "args": { + "External id": 1440967,"Record function id": 0, "Sequence number": 15349051, "Fwd thread id": 1, "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083536.438, "dur": 7.931, + "args": { + "External id": 1440968,"Sequence number": 15349051, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6343 + } + }, + { + "ph": "f", "id": 284, "pid": 2338706, "tid": 2379422, "ts": 6413854083536.438, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083538.401, "dur": 5.837, + "args": { + "External id": 1440969,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083540.061, "dur": 4.024, + "args": { + "External id": 1440970,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854083547.706, "dur": 22.803, + "args": { + "External id": 1440971,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083579.589, "dur": 9.128, + "args": { + "External id": 1440972,"Record function id": 0, "Sequence number": 15349050, "Fwd thread id": 1, "Ev Idx": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083580.711, "dur": 5.498, + "args": { + "External id": 1440973,"Sequence number": 15349050, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6348 + } + }, + { + "ph": "f", "id": 285, "pid": 2338706, "tid": 2379422, "ts": 6413854083580.711, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083581.672, "dur": 4.337, + "args": { + "External id": 1440974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083582.836, "dur": 2.551, + "args": { + "External id": 1440975,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083584.605, "dur": 0.662, + "args": { + "External id": 1440976,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854083593.113, "dur": 5.610, + "args": { + "External id": 1440977,"Record function id": 0, "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854083594.723, "dur": 3.495, + "args": { + "External id": 1440978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854083595.758, "dur": 1.731, + "args": { + "External id": 1440979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854083596.188, "dur": 1.209, + "args": { + "External id": 1440980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083601.765, "dur": 9.441, + "args": { + "External id": 1440981,"Record function id": 0, "Sequence number": 15349049, "Fwd thread id": 1, "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083603.087, "dur": 5.051, + "args": { + "External id": 1440982,"Sequence number": 15349049, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6357 + } + }, + { + "ph": "f", "id": 286, "pid": 2338706, "tid": 2379422, "ts": 6413854083603.087, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083604.545, "dur": 3.448, + "args": { + "External id": 1440983,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083607.081, "dur": 0.823, + "args": { + "External id": 1440984,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083614.267, "dur": 101.218, + "args": { + "External id": 1440985,"Record function id": 0, "Sequence number": 15349048, "Fwd thread id": 1, "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083615.106, "dur": 90.514, + "args": { + "External id": 1440986,"Sequence number": 15349048, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6361 + } + }, + { + "ph": "f", "id": 287, "pid": 2338706, "tid": 2379422, "ts": 6413854083615.106, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083618.258, "dur": 3.150, + "args": { + "External id": 1440987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083618.724, "dur": 2.248, + "args": { + "External id": 1440988,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083620.385, "dur": 0.484, + "args": { + "External id": 1440989,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854083624.197, "dur": 34.033, + "args": { + "External id": 1440990,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083659.208, "dur": 4.032, + "args": { + "External id": 1440991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083659.872, "dur": 2.784, + "args": { + "External id": 1440992,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083661.573, "dur": 0.963, + "args": { + "External id": 1440993,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083664.485, "dur": 5.240, + "args": { + "External id": 1440994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083665.262, "dur": 3.907, + "args": { + "External id": 1440995,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083666.410, "dur": 2.683, + "args": { + "External id": 1440996,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854083673.133, "dur": 31.711, + "args": { + "External id": 1440997,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083719.870, "dur": 25.665, + "args": { + "External id": 1440998,"Record function id": 0, "Sequence number": 15349047, "Fwd thread id": 1, "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083720.797, "dur": 4.319, + "args": { + "External id": 1440999,"Sequence number": 15349047, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6374 + } + }, + { + "ph": "f", "id": 288, "pid": 2338706, "tid": 2379422, "ts": 6413854083720.797, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083722.627, "dur": 2.341, + "args": { + "External id": 1441000,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083723.883, "dur": 0.958, + "args": { + "External id": 1441001,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854083727.370, "dur": 15.890, + "args": { + "External id": 1441002,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083749.726, "dur": 11.865, + "args": { + "External id": 1441003,"Record function id": 0, "Sequence number": 15349046, "Fwd thread id": 1, "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854083750.887, "dur": 7.284, + "args": { + "External id": 1441004,"Sequence number": 15349046, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6379 + } + }, + { + "ph": "f", "id": 289, "pid": 2338706, "tid": 2379422, "ts": 6413854083750.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854083751.749, "dur": 6.249, + "args": { + "External id": 1441005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854083752.477, "dur": 4.939, + "args": { + "External id": 1441006,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854083756.710, "dur": 0.593, + "args": { + "External id": 1441007,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854083765.744, "dur": 6.285, + "args": { + "External id": 1441008,"Record function id": 0, "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854083767.451, "dur": 4.107, + "args": { + "External id": 1441009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854083768.805, "dur": 2.166, + "args": { + "External id": 1441010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854083769.722, "dur": 1.173, + "args": { + "External id": 1441011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854083776.071, "dur": 457.735, + "args": { + "External id": 1441012,"Record function id": 0, "Sequence number": 15349045, "Fwd thread id": 1, "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854083777.798, "dur": 415.561, + "args": { + "External id": 1441013,"Sequence number": 15349045, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6388 + } + }, + { + "ph": "f", "id": 290, "pid": 2338706, "tid": 2379422, "ts": 6413854083777.798, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854083814.378, "dur": 2.500, + "args": { + "External id": 1441014,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854083815.634, "dur": 1.099, + "args": { + "External id": 1441015,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854083833.871, "dur": 3.742, + "args": { + "External id": 1441016,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854083847.743, "dur": 1.806, + "args": { + "External id": 1441017,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084037.468, "dur": 4.691, + "args": { + "External id": 1441018,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854084046.773, "dur": 78.501, + "args": { + "External id": 1441019,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084094.643, "dur": 1.171, + "args": { + "External id": 1441020,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854084132.929, "dur": 33.192, + "args": { + "External id": 1441021,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854084134.867, "dur": 31.046, + "args": { + "External id": 1441022,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084142.068, "dur": 5.093, + "args": { + "External id": 1441023,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854084148.902, "dur": 16.493, + "args": { + "External id": 1441024,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854084171.675, "dur": 3.106, + "args": { + "External id": 1441025,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084173.148, "dur": 1.533, + "args": { + "External id": 1441026,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084182.489, "dur": 2.654, + "args": { + "External id": 1441027,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084184.154, "dur": 0.901, + "args": { + "External id": 1441028,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854084208.861, "dur": 16.931, + "args": { + "External id": 1441029,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854084247.762, "dur": 13.390, + "args": { + "External id": 1441030,"Record function id": 0, "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854084250.206, "dur": 10.069, + "args": { + "External id": 1441031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854084252.786, "dur": 6.305, + "args": { + "External id": 1441032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854084253.937, "dur": 5.040, + "args": { + "External id": 1441033,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084265.022, "dur": 8.713, + "args": { + "External id": 1441034,"Record function id": 0, "Sequence number": 15349044, "Fwd thread id": 1, "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084266.346, "dur": 1.683, + "args": { + "External id": 1441035,"Sequence number": 15349044, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6410 + } + }, + { + "ph": "f", "id": 291, "pid": 2338706, "tid": 2379422, "ts": 6413854084266.346, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854084277.622, "dur": 434.955, + "args": { + "External id": 1441036,"Record function id": 0, "Sequence number": 15349043, "Fwd thread id": 1, "Ev Idx": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854084278.843, "dur": 419.328, + "args": { + "External id": 1441037,"Sequence number": 15349043, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6412 + } + }, + { + "ph": "f", "id": 292, "pid": 2338706, "tid": 2379422, "ts": 6413854084278.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084315.336, "dur": 8.826, + "args": { + "External id": 1441038,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854084320.742, "dur": 3.102, + "args": { + "External id": 1441039,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 6414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084328.131, "dur": 5.854, + "args": { + "External id": 1441040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084330.346, "dur": 3.007, + "args": { + "External id": 1441041,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084332.522, "dur": 0.687, + "args": { + "External id": 1441042,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413854084337.748, "dur": 92.062, + "args": { + "External id": 1441043,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 6418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084341.119, "dur": 4.138, + "args": { + "External id": 1441044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 6419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084341.908, "dur": 2.791, + "args": { + "External id": 1441045,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084343.549, "dur": 1.040, + "args": { + "External id": 1441046,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413854084346.533, "dur": 82.866, + "args": { + "External id": 1441047,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854084348.225, "dur": 80.294, + "args": { + "External id": 1441048,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854084434.359, "dur": 5.947, + "args": { + "External id": 1441049,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 6424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084436.083, "dur": 4.069, + "args": { + "External id": 1441050,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854084477.822, "dur": 3.972, + "args": { + "External id": 1441051,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854084483.141, "dur": 2.243, + "args": { + "External id": 1441052,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854084486.707, "dur": 2.398, + "args": { + "External id": 1441053,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084519.111, "dur": 2.765, + "args": { + "External id": 1441054,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084520.521, "dur": 1.209, + "args": { + "External id": 1441055,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413854084548.627, "dur": 128.636, + "args": { + "External id": 1441056,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 6431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854084556.696, "dur": 5.889, + "args": { + "External id": 1441057,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084560.964, "dur": 0.876, + "args": { + "External id": 1441058,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854084564.382, "dur": 5.955, + "args": { + "External id": 1441059,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 6434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084568.341, "dur": 0.730, + "args": { + "External id": 1441060,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 6435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854084571.809, "dur": 3.013, + "args": { + "External id": 1441061,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084573.704, "dur": 0.761, + "args": { + "External id": 1441062,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854084576.284, "dur": 5.615, + "args": { + "External id": 1441063,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084578.849, "dur": 2.344, + "args": { + "External id": 1441064,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 6439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854084586.198, "dur": 5.842, + "args": { + "External id": 1441065,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 6440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084591.066, "dur": 0.646, + "args": { + "External id": 1441066,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 6441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084593.385, "dur": 7.252, + "args": { + "External id": 1441067,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 6442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854084598.131, "dur": 2.344, + "args": { + "External id": 1441068,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 6443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854084604.072, "dur": 3.039, + "args": { + "External id": 1441069,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 6444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084606.083, "dur": 0.652, + "args": { + "External id": 1441070,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 6445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084608.287, "dur": 3.100, + "args": { + "External id": 1441071,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084609.455, "dur": 1.833, + "args": { + "External id": 1441072,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854084612.459, "dur": 49.207, + "args": { + "External id": 1441073,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 6448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084664.039, "dur": 1.478, + "args": { + "External id": 1441074,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 6449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854084666.615, "dur": 3.411, + "args": { + "External id": 1441075,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 6450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084668.786, "dur": 0.316, + "args": { + "External id": 1441076,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 6451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084672.489, "dur": 3.457, + "args": { + "External id": 1441077,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 6452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854084721.583, "dur": 8.823, + "args": { + "External id": 1441078,"Record function id": 0, "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854084723.331, "dur": 6.273, + "args": { + "External id": 1441079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854084725.273, "dur": 3.259, + "args": { + "External id": 1441080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854084726.366, "dur": 2.009, + "args": { + "External id": 1441081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084733.971, "dur": 9.938, + "args": { + "External id": 1441082,"Record function id": 0, "Sequence number": 15349042, "Fwd thread id": 1, "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084735.631, "dur": 4.500, + "args": { + "External id": 1441083,"Sequence number": 15349042, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6458 + } + }, + { + "ph": "f", "id": 293, "pid": 2338706, "tid": 2379422, "ts": 6413854084735.631, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084738.029, "dur": 1.893, + "args": { + "External id": 1441084,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084738.973, "dur": 0.820, + "args": { + "External id": 1441085,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084747.139, "dur": 110.692, + "args": { + "External id": 1441086,"Record function id": 0, "Sequence number": 15349041, "Fwd thread id": 1, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084748.073, "dur": 102.628, + "args": { + "External id": 1441087,"Sequence number": 15349041, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6462 + } + }, + { + "ph": "f", "id": 294, "pid": 2338706, "tid": 2379422, "ts": 6413854084748.073, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084752.204, "dur": 6.449, + "args": { + "External id": 1441088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084753.453, "dur": 4.640, + "args": { + "External id": 1441089,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084757.222, "dur": 0.700, + "args": { + "External id": 1441090,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854084759.783, "dur": 40.877, + "args": { + "External id": 1441091,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084801.662, "dur": 4.749, + "args": { + "External id": 1441092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084802.428, "dur": 3.346, + "args": { + "External id": 1441093,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084804.444, "dur": 1.165, + "args": { + "External id": 1441094,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084808.607, "dur": 6.273, + "args": { + "External id": 1441095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084809.661, "dur": 4.473, + "args": { + "External id": 1441096,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084813.600, "dur": 0.467, + "args": { + "External id": 1441097,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854084815.568, "dur": 34.372, + "args": { + "External id": 1441098,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084862.627, "dur": 9.388, + "args": { + "External id": 1441099,"Record function id": 0, "Sequence number": 15349040, "Fwd thread id": 1, "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084863.896, "dur": 6.920, + "args": { + "External id": 1441100,"Sequence number": 15349040, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6475 + } + }, + { + "ph": "f", "id": 295, "pid": 2338706, "tid": 2379422, "ts": 6413854084863.896, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084865.934, "dur": 4.746, + "args": { + "External id": 1441101,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084867.113, "dur": 3.458, + "args": { + "External id": 1441102,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084875.937, "dur": 11.024, + "args": { + "External id": 1441103,"Record function id": 0, "Sequence number": 15349039, "Fwd thread id": 1, "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084877.040, "dur": 7.411, + "args": { + "External id": 1441104,"Sequence number": 15349039, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6479 + } + }, + { + "ph": "f", "id": 296, "pid": 2338706, "tid": 2379422, "ts": 6413854084877.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084878.282, "dur": 5.962, + "args": { + "External id": 1441105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084881.564, "dur": 2.216, + "args": { + "External id": 1441106,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084883.193, "dur": 0.461, + "args": { + "External id": 1441107,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854084890.870, "dur": 5.986, + "args": { + "External id": 1441108,"Record function id": 0, "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854084892.926, "dur": 3.362, + "args": { + "External id": 1441109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854084893.908, "dur": 2.139, + "args": { + "External id": 1441110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854084894.722, "dur": 1.232, + "args": { + "External id": 1441111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084899.858, "dur": 8.228, + "args": { + "External id": 1441112,"Record function id": 0, "Sequence number": 15349038, "Fwd thread id": 1, "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084901.108, "dur": 3.516, + "args": { + "External id": 1441113,"Sequence number": 15349038, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6488 + } + }, + { + "ph": "f", "id": 297, "pid": 2338706, "tid": 2379422, "ts": 6413854084901.108, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854084902.578, "dur": 1.895, + "args": { + "External id": 1441114,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854084903.693, "dur": 0.642, + "args": { + "External id": 1441115,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084911.153, "dur": 121.443, + "args": { + "External id": 1441116,"Record function id": 0, "Sequence number": 15349037, "Fwd thread id": 1, "Ev Idx": 6491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854084914.034, "dur": 107.448, + "args": { + "External id": 1441117,"Sequence number": 15349037, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6492 + } + }, + { + "ph": "f", "id": 298, "pid": 2338706, "tid": 2379422, "ts": 6413854084914.034, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084917.395, "dur": 3.142, + "args": { + "External id": 1441118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084917.831, "dur": 2.262, + "args": { + "External id": 1441119,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084919.408, "dur": 0.593, + "args": { + "External id": 1441120,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854084921.176, "dur": 31.964, + "args": { + "External id": 1441121,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084954.139, "dur": 5.772, + "args": { + "External id": 1441122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084954.865, "dur": 4.562, + "args": { + "External id": 1441123,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084958.534, "dur": 0.777, + "args": { + "External id": 1441124,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854084961.749, "dur": 3.878, + "args": { + "External id": 1441125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854084962.881, "dur": 2.128, + "args": { + "External id": 1441126,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854084964.391, "dur": 0.538, + "args": { + "External id": 1441127,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854084966.035, "dur": 54.079, + "args": { + "External id": 1441128,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085039.294, "dur": 71.590, + "args": { + "External id": 1441129,"Record function id": 0, "Sequence number": 15349036, "Fwd thread id": 1, "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085040.642, "dur": 5.612, + "args": { + "External id": 1441130,"Sequence number": 15349036, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6505 + } + }, + { + "ph": "f", "id": 299, "pid": 2338706, "tid": 2379422, "ts": 6413854085040.642, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085042.949, "dur": 3.167, + "args": { + "External id": 1441131,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085044.346, "dur": 1.676, + "args": { + "External id": 1441132,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854085049.160, "dur": 57.951, + "args": { + "External id": 1441133,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085117.080, "dur": 13.622, + "args": { + "External id": 1441134,"Record function id": 0, "Sequence number": 15349035, "Fwd thread id": 1, "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085118.518, "dur": 9.145, + "args": { + "External id": 1441135,"Sequence number": 15349035, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6510 + } + }, + { + "ph": "f", "id": 300, "pid": 2338706, "tid": 2379422, "ts": 6413854085118.518, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854085122.660, "dur": 4.769, + "args": { + "External id": 1441136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854085124.036, "dur": 2.654, + "args": { + "External id": 1441137,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085126.130, "dur": 0.448, + "args": { + "External id": 1441138,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854085135.340, "dur": 6.800, + "args": { + "External id": 1441139,"Record function id": 0, "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854085136.848, "dur": 4.724, + "args": { + "External id": 1441140,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854085138.469, "dur": 2.642, + "args": { + "External id": 1441141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854085139.071, "dur": 1.945, + "args": { + "External id": 1441142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854085146.450, "dur": 458.852, + "args": { + "External id": 1441143,"Record function id": 0, "Sequence number": 15349034, "Fwd thread id": 1, "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854085148.005, "dur": 420.133, + "args": { + "External id": 1441144,"Sequence number": 15349034, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 6519 + } + }, + { + "ph": "f", "id": 301, "pid": 2338706, "tid": 2379422, "ts": 6413854085148.005, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413854085172.289, "dur": 36.699, + "args": { + "External id": 1441145,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854085173.972, "dur": 34.769, + "args": { + "External id": 1441146,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854085177.336, "dur": 6.601, + "args": { + "External id": 1441147,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854085180.083, "dur": 3.251, + "args": { + "External id": 1441148,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854085185.567, "dur": 22.649, + "args": { + "External id": 1441149,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085221.011, "dur": 5.567, + "args": { + "External id": 1441150,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085225.036, "dur": 1.372, + "args": { + "External id": 1441151,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085230.573, "dur": 1.915, + "args": { + "External id": 1441152,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085231.748, "dur": 0.652, + "args": { + "External id": 1441153,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854085245.109, "dur": 4.540, + "args": { + "External id": 1441154,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854085263.246, "dur": 2.177, + "args": { + "External id": 1441155,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085451.427, "dur": 4.899, + "args": { + "External id": 1441156,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854085460.979, "dur": 34.534, + "args": { + "External id": 1441157,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085471.034, "dur": 0.696, + "args": { + "External id": 1441158,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854085502.171, "dur": 31.956, + "args": { + "External id": 1441159,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854085504.353, "dur": 29.529, + "args": { + "External id": 1441160,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085508.771, "dur": 4.828, + "args": { + "External id": 1441161,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854085517.652, "dur": 15.718, + "args": { + "External id": 1441162,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854085538.824, "dur": 2.913, + "args": { + "External id": 1441163,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085540.266, "dur": 1.311, + "args": { + "External id": 1441164,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085548.847, "dur": 2.714, + "args": { + "External id": 1441165,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085550.091, "dur": 1.363, + "args": { + "External id": 1441166,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085553.812, "dur": 2.453, + "args": { + "External id": 1441167,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085555.085, "dur": 1.097, + "args": { + "External id": 1441168,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854085584.839, "dur": 19.144, + "args": { + "External id": 1441169,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854085615.170, "dur": 8.070, + "args": { + "External id": 1441170,"Record function id": 0, "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854085617.475, "dur": 5.119, + "args": { + "External id": 1441171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854085619.409, "dur": 2.199, + "args": { + "External id": 1441172,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854085620.183, "dur": 1.336, + "args": { + "External id": 1441173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085626.987, "dur": 8.329, + "args": { + "External id": 1441174,"Record function id": 0, "Sequence number": 15349033, "Fwd thread id": 1, "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085628.288, "dur": 4.043, + "args": { + "External id": 1441175,"Sequence number": 15349033, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6550 + } + }, + { + "ph": "f", "id": 302, "pid": 2338706, "tid": 2379422, "ts": 6413854085628.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085629.834, "dur": 2.324, + "args": { + "External id": 1441176,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085630.880, "dur": 1.147, + "args": { + "External id": 1441177,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085639.309, "dur": 144.276, + "args": { + "External id": 1441178,"Record function id": 0, "Sequence number": 15349032, "Fwd thread id": 1, "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085642.889, "dur": 132.320, + "args": { + "External id": 1441179,"Sequence number": 15349032, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6554 + } + }, + { + "ph": "f", "id": 303, "pid": 2338706, "tid": 2379422, "ts": 6413854085642.889, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854085647.400, "dur": 5.366, + "args": { + "External id": 1441180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854085648.820, "dur": 3.354, + "args": { + "External id": 1441181,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085650.961, "dur": 1.043, + "args": { + "External id": 1441182,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854085654.059, "dur": 71.249, + "args": { + "External id": 1441183,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854085726.789, "dur": 6.440, + "args": { + "External id": 1441184,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854085727.715, "dur": 5.015, + "args": { + "External id": 1441185,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085731.979, "dur": 0.624, + "args": { + "External id": 1441186,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854085735.076, "dur": 3.365, + "args": { + "External id": 1441187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854085735.905, "dur": 2.001, + "args": { + "External id": 1441188,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085737.259, "dur": 0.579, + "args": { + "External id": 1441189,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854085738.905, "dur": 35.688, + "args": { + "External id": 1441190,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085789.488, "dur": 10.935, + "args": { + "External id": 1441191,"Record function id": 0, "Sequence number": 15349031, "Fwd thread id": 1, "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085790.749, "dur": 6.504, + "args": { + "External id": 1441192,"Sequence number": 15349031, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6567 + } + }, + { + "ph": "f", "id": 304, "pid": 2338706, "tid": 2379422, "ts": 6413854085790.749, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085792.926, "dur": 4.159, + "args": { + "External id": 1441193,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085794.009, "dur": 2.903, + "args": { + "External id": 1441194,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085804.763, "dur": 10.267, + "args": { + "External id": 1441195,"Record function id": 0, "Sequence number": 15349030, "Fwd thread id": 1, "Ev Idx": 6570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085805.727, "dur": 6.030, + "args": { + "External id": 1441196,"Sequence number": 15349030, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6571 + } + }, + { + "ph": "f", "id": 305, "pid": 2338706, "tid": 2379422, "ts": 6413854085805.727, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854085806.776, "dur": 4.778, + "args": { + "External id": 1441197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854085807.438, "dur": 3.625, + "args": { + "External id": 1441198,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085810.470, "dur": 0.489, + "args": { + "External id": 1441199,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854085819.090, "dur": 5.284, + "args": { + "External id": 1441200,"Record function id": 0, "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854085820.683, "dur": 3.208, + "args": { + "External id": 1441201,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854085821.821, "dur": 1.828, + "args": { + "External id": 1441202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854085822.523, "dur": 1.040, + "args": { + "External id": 1441203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085827.409, "dur": 7.729, + "args": { + "External id": 1441204,"Record function id": 0, "Sequence number": 15349029, "Fwd thread id": 1, "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854085828.461, "dur": 3.911, + "args": { + "External id": 1441205,"Sequence number": 15349029, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6580 + } + }, + { + "ph": "f", "id": 306, "pid": 2338706, "tid": 2379422, "ts": 6413854085828.461, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854085829.992, "dur": 2.240, + "args": { + "External id": 1441206,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854085830.829, "dur": 1.263, + "args": { + "External id": 1441207,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854085839.349, "dur": 443.464, + "args": { + "External id": 1441208,"Record function id": 0, "Sequence number": 15349028, "Fwd thread id": 1, "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854085840.945, "dur": 416.388, + "args": { + "External id": 1441209,"Sequence number": 15349028, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6584 + } + }, + { + "ph": "f", "id": 307, "pid": 2338706, "tid": 2379422, "ts": 6413854085840.945, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854085859.548, "dur": 9.624, + "args": { + "External id": 1441210,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085862.377, "dur": 6.333, + "args": { + "External id": 1441211,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854085871.188, "dur": 3.508, + "args": { + "External id": 1441212,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085872.961, "dur": 1.551, + "args": { + "External id": 1441213,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854085876.348, "dur": 3.760, + "args": { + "External id": 1441214,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854085878.008, "dur": 1.895, + "args": { + "External id": 1441215,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854085905.481, "dur": 323.515, + "args": { + "External id": 1441216,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 6591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854086020.703, "dur": 4.951, + "args": { + "External id": 1441217,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854086027.998, "dur": 3.058, + "args": { + "External id": 1441218,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854086032.464, "dur": 2.493, + "args": { + "External id": 1441219,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854086036.365, "dur": 2.491, + "args": { + "External id": 1441220,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086120.466, "dur": 3.719, + "args": { + "External id": 1441221,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086121.757, "dur": 2.067, + "args": { + "External id": 1441222,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854086127.996, "dur": 32.649, + "args": { + "External id": 1441223,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086133.726, "dur": 5.882, + "args": { + "External id": 1441224,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086162.286, "dur": 1.936, + "args": { + "External id": 1441225,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086163.446, "dur": 0.704, + "args": { + "External id": 1441226,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854086165.372, "dur": 14.101, + "args": { + "External id": 1441227,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086167.885, "dur": 0.545, + "args": { + "External id": 1441228,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854086243.472, "dur": 4.176, + "args": { + "External id": 1441229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854086250.704, "dur": 0.601, + "args": { + "External id": 1441230,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854086253.281, "dur": 0.853, + "args": { + "External id": 1441231,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854086294.827, "dur": 240.597, + "args": { + "External id": 1441232,"Record function id": 0, "Sequence number": 15349027, "Fwd thread id": 1, "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854086297.260, "dur": 229.539, + "args": { + "External id": 1441233,"Sequence number": 15349027, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6608 + } + }, + { + "ph": "f", "id": 308, "pid": 2338706, "tid": 2379422, "ts": 6413854086297.260, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854086320.666, "dur": 47.421, + "args": { + "External id": 1441234,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086324.611, "dur": 4.816, + "args": { + "External id": 1441235,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854086331.127, "dur": 36.143, + "args": { + "External id": 1441236,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 6611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854086379.244, "dur": 5.866, + "args": { + "External id": 1441237,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086382.204, "dur": 2.557, + "args": { + "External id": 1441238,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854086542.602, "dur": 165.545, + "args": { + "External id": 1441239,"Record function id": 0, "Sequence number": 15349026, "Fwd thread id": 1, "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854086544.556, "dur": 155.687, + "args": { + "External id": 1441240,"Sequence number": 15349026, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6615 + } + }, + { + "ph": "f", "id": 309, "pid": 2338706, "tid": 2379422, "ts": 6413854086544.556, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854086556.582, "dur": 49.120, + "args": { + "External id": 1441241,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086560.369, "dur": 3.257, + "args": { + "External id": 1441242,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854086567.330, "dur": 37.720, + "args": { + "External id": 1441243,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 6618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854086612.964, "dur": 5.344, + "args": { + "External id": 1441244,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086615.772, "dur": 2.258, + "args": { + "External id": 1441245,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086714.608, "dur": 16.340, + "args": { + "External id": 1441246,"Record function id": 0, "Sequence number": 15349025, "Fwd thread id": 1, "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086716.097, "dur": 11.672, + "args": { + "External id": 1441247,"Sequence number": 15349025, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6622 + } + }, + { + "ph": "f", "id": 310, "pid": 2338706, "tid": 2379422, "ts": 6413854086716.097, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086719.021, "dur": 8.509, + "args": { + "External id": 1441248,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086720.690, "dur": 6.667, + "args": { + "External id": 1441249,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086734.630, "dur": 8.078, + "args": { + "External id": 1441250,"Record function id": 0, "Sequence number": 15349024, "Fwd thread id": 1, "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086735.721, "dur": 4.284, + "args": { + "External id": 1441251,"Sequence number": 15349024, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6626 + } + }, + { + "ph": "f", "id": 311, "pid": 2338706, "tid": 2379422, "ts": 6413854086735.721, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086737.424, "dur": 2.442, + "args": { + "External id": 1441252,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086738.506, "dur": 1.223, + "args": { + "External id": 1441253,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086746.031, "dur": 9.900, + "args": { + "External id": 1441254,"Record function id": 0, "Sequence number": 15349023, "Fwd thread id": 1, "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086747.042, "dur": 6.423, + "args": { + "External id": 1441255,"Sequence number": 15349023, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6630 + } + }, + { + "ph": "f", "id": 312, "pid": 2338706, "tid": 2379422, "ts": 6413854086747.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086749.013, "dur": 4.327, + "args": { + "External id": 1441256,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086752.271, "dur": 0.945, + "args": { + "External id": 1441257,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086760.324, "dur": 9.605, + "args": { + "External id": 1441258,"Record function id": 0, "Sequence number": 15349022, "Fwd thread id": 1, "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086761.793, "dur": 3.927, + "args": { + "External id": 1441259,"Sequence number": 15349022, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6634 + } + }, + { + "ph": "f", "id": 313, "pid": 2338706, "tid": 2379422, "ts": 6413854086761.793, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086763.530, "dur": 2.045, + "args": { + "External id": 1441260,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086764.338, "dur": 1.110, + "args": { + "External id": 1441261,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086773.358, "dur": 165.192, + "args": { + "External id": 1441262,"Record function id": 0, "Sequence number": 15349021, "Fwd thread id": 1, "Ev Idx": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086774.589, "dur": 156.764, + "args": { + "External id": 1441263,"Sequence number": 15349021, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6638 + } + }, + { + "ph": "f", "id": 314, "pid": 2338706, "tid": 2379422, "ts": 6413854086774.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854086780.085, "dur": 9.436, + "args": { + "External id": 1441264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854086784.769, "dur": 4.082, + "args": { + "External id": 1441265,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086787.127, "dur": 1.358, + "args": { + "External id": 1441266,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854086791.163, "dur": 70.829, + "args": { + "External id": 1441267,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854086863.352, "dur": 10.120, + "args": { + "External id": 1441268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854086864.500, "dur": 8.265, + "args": { + "External id": 1441269,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086870.192, "dur": 2.410, + "args": { + "External id": 1441270,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854086877.344, "dur": 3.707, + "args": { + "External id": 1441271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854086878.852, "dur": 1.773, + "args": { + "External id": 1441272,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854086880.211, "dur": 0.340, + "args": { + "External id": 1441273,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854086881.632, "dur": 48.823, + "args": { + "External id": 1441274,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086943.696, "dur": 7.462, + "args": { + "External id": 1441275,"Record function id": 0, "Sequence number": 15349020, "Fwd thread id": 1, "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086944.638, "dur": 4.544, + "args": { + "External id": 1441276,"Sequence number": 15349020, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6651 + } + }, + { + "ph": "f", "id": 315, "pid": 2338706, "tid": 2379422, "ts": 6413854086944.638, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854086946.513, "dur": 2.513, + "args": { + "External id": 1441277,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854086947.687, "dur": 1.182, + "args": { + "External id": 1441278,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086954.591, "dur": 164.016, + "args": { + "External id": 1441279,"Record function id": 0, "Sequence number": 15349019, "Fwd thread id": 1, "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854086955.689, "dur": 157.661, + "args": { + "External id": 1441280,"Sequence number": 15349019, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6655 + } + }, + { + "ph": "f", "id": 316, "pid": 2338706, "tid": 2379422, "ts": 6413854086955.689, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087105.191, "dur": 7.882, + "args": { + "External id": 1441281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087108.212, "dur": 3.893, + "args": { + "External id": 1441282,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087110.650, "dur": 0.943, + "args": { + "External id": 1441283,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087126.994, "dur": 10.236, + "args": { + "External id": 1441284,"Record function id": 0, "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087128.696, "dur": 7.655, + "args": { + "External id": 1441285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087131.594, "dur": 4.324, + "args": { + "External id": 1441286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087132.846, "dur": 2.981, + "args": { + "External id": 1441287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087140.638, "dur": 7.140, + "args": { + "External id": 1441288,"Record function id": 0, "Sequence number": 15349018, "Fwd thread id": 1, "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087142.015, "dur": 3.306, + "args": { + "External id": 1441289,"Sequence number": 15349018, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6664 + } + }, + { + "ph": "f", "id": 317, "pid": 2338706, "tid": 2379422, "ts": 6413854087142.015, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087143.061, "dur": 2.105, + "args": { + "External id": 1441290,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087143.829, "dur": 1.187, + "args": { + "External id": 1441291,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087151.438, "dur": 118.691, + "args": { + "External id": 1441292,"Record function id": 0, "Sequence number": 15349017, "Fwd thread id": 1, "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087154.855, "dur": 105.547, + "args": { + "External id": 1441293,"Sequence number": 15349017, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6668 + } + }, + { + "ph": "f", "id": 318, "pid": 2338706, "tid": 2379422, "ts": 6413854087154.855, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087158.641, "dur": 2.933, + "args": { + "External id": 1441294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087159.282, "dur": 1.833, + "args": { + "External id": 1441295,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087160.417, "dur": 0.583, + "args": { + "External id": 1441296,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854087162.464, "dur": 42.611, + "args": { + "External id": 1441297,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087206.273, "dur": 6.568, + "args": { + "External id": 1441298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087206.987, "dur": 5.345, + "args": { + "External id": 1441299,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087211.474, "dur": 0.742, + "args": { + "External id": 1441300,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087214.415, "dur": 5.715, + "args": { + "External id": 1441301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087215.412, "dur": 4.264, + "args": { + "External id": 1441302,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087217.207, "dur": 2.404, + "args": { + "External id": 1441303,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854087220.576, "dur": 39.026, + "args": { + "External id": 1441304,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087275.418, "dur": 38.754, + "args": { + "External id": 1441305,"Record function id": 0, "Sequence number": 15349016, "Fwd thread id": 1, "Ev Idx": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087276.398, "dur": 6.913, + "args": { + "External id": 1441306,"Sequence number": 15349016, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6681 + } + }, + { + "ph": "f", "id": 319, "pid": 2338706, "tid": 2379422, "ts": 6413854087276.398, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087278.286, "dur": 4.851, + "args": { + "External id": 1441307,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087279.638, "dur": 3.320, + "args": { + "External id": 1441308,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854087286.862, "dur": 24.622, + "args": { + "External id": 1441309,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087318.181, "dur": 9.482, + "args": { + "External id": 1441310,"Record function id": 0, "Sequence number": 15349015, "Fwd thread id": 1, "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087321.307, "dur": 4.732, + "args": { + "External id": 1441311,"Sequence number": 15349015, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6686 + } + }, + { + "ph": "f", "id": 320, "pid": 2338706, "tid": 2379422, "ts": 6413854087321.307, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087322.347, "dur": 3.424, + "args": { + "External id": 1441312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087323.267, "dur": 1.997, + "args": { + "External id": 1441313,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087324.697, "dur": 0.432, + "args": { + "External id": 1441314,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087331.691, "dur": 5.739, + "args": { + "External id": 1441315,"Record function id": 0, "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087333.492, "dur": 3.450, + "args": { + "External id": 1441316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087334.724, "dur": 1.790, + "args": { + "External id": 1441317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087335.414, "dur": 1.008, + "args": { + "External id": 1441318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087340.976, "dur": 10.256, + "args": { + "External id": 1441319,"Record function id": 0, "Sequence number": 15349014, "Fwd thread id": 1, "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087342.438, "dur": 6.265, + "args": { + "External id": 1441320,"Sequence number": 15349014, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6695 + } + }, + { + "ph": "f", "id": 321, "pid": 2338706, "tid": 2379422, "ts": 6413854087342.438, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087343.667, "dur": 4.883, + "args": { + "External id": 1441321,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087347.379, "dur": 1.069, + "args": { + "External id": 1441322,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087354.656, "dur": 102.398, + "args": { + "External id": 1441323,"Record function id": 0, "Sequence number": 15349013, "Fwd thread id": 1, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087355.683, "dur": 91.492, + "args": { + "External id": 1441324,"Sequence number": 15349013, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6699 + } + }, + { + "ph": "f", "id": 322, "pid": 2338706, "tid": 2379422, "ts": 6413854087355.683, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087358.716, "dur": 2.727, + "args": { + "External id": 1441325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087359.264, "dur": 1.709, + "args": { + "External id": 1441326,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087360.426, "dur": 0.441, + "args": { + "External id": 1441327,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854087362.292, "dur": 37.031, + "args": { + "External id": 1441328,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087403.518, "dur": 3.514, + "args": { + "External id": 1441329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087404.010, "dur": 2.329, + "args": { + "External id": 1441330,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087405.316, "dur": 0.907, + "args": { + "External id": 1441331,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087408.328, "dur": 3.460, + "args": { + "External id": 1441332,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087409.327, "dur": 1.883, + "args": { + "External id": 1441333,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087410.803, "dur": 0.340, + "args": { + "External id": 1441334,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854087414.869, "dur": 31.380, + "args": { + "External id": 1441335,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087462.001, "dur": 24.868, + "args": { + "External id": 1441336,"Record function id": 0, "Sequence number": 15349012, "Fwd thread id": 1, "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087463.041, "dur": 4.059, + "args": { + "External id": 1441337,"Sequence number": 15349012, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6712 + } + }, + { + "ph": "f", "id": 323, "pid": 2338706, "tid": 2379422, "ts": 6413854087463.041, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087464.715, "dur": 2.233, + "args": { + "External id": 1441338,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087465.651, "dur": 1.156, + "args": { + "External id": 1441339,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854087469.542, "dur": 15.029, + "args": { + "External id": 1441340,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087490.582, "dur": 7.818, + "args": { + "External id": 1441341,"Record function id": 0, "Sequence number": 15349011, "Fwd thread id": 1, "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087491.487, "dur": 4.102, + "args": { + "External id": 1441342,"Sequence number": 15349011, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6717 + } + }, + { + "ph": "f", "id": 324, "pid": 2338706, "tid": 2379422, "ts": 6413854087491.487, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087492.234, "dur": 3.157, + "args": { + "External id": 1441343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087492.963, "dur": 1.890, + "args": { + "External id": 1441344,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087494.266, "dur": 0.473, + "args": { + "External id": 1441345,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087502.570, "dur": 5.019, + "args": { + "External id": 1441346,"Record function id": 0, "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087503.837, "dur": 3.276, + "args": { + "External id": 1441347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087504.750, "dur": 1.440, + "args": { + "External id": 1441348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087505.171, "dur": 0.912, + "args": { + "External id": 1441349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854087512.252, "dur": 366.825, + "args": { + "External id": 1441350,"Record function id": 0, "Sequence number": 15349010, "Fwd thread id": 1, "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854087513.665, "dur": 336.328, + "args": { + "External id": 1441351,"Sequence number": 15349010, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6726 + } + }, + { + "ph": "f", "id": 325, "pid": 2338706, "tid": 2379422, "ts": 6413854087513.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087554.135, "dur": 4.413, + "args": { + "External id": 1441352,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087557.220, "dur": 1.203, + "args": { + "External id": 1441353,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854087574.021, "dur": 6.502, + "args": { + "External id": 1441354,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854087590.602, "dur": 2.212, + "args": { + "External id": 1441355,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087748.972, "dur": 1.745, + "args": { + "External id": 1441356,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854087754.933, "dur": 33.297, + "args": { + "External id": 1441357,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087765.319, "dur": 0.693, + "args": { + "External id": 1441358,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854087794.251, "dur": 32.556, + "args": { + "External id": 1441359,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854087796.161, "dur": 30.435, + "args": { + "External id": 1441360,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087803.131, "dur": 4.526, + "args": { + "External id": 1441361,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854087809.544, "dur": 16.522, + "args": { + "External id": 1441362,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854087831.266, "dur": 2.656, + "args": { + "External id": 1441363,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087832.836, "dur": 0.951, + "args": { + "External id": 1441364,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087840.813, "dur": 2.263, + "args": { + "External id": 1441365,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854087841.971, "dur": 0.996, + "args": { + "External id": 1441366,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854087862.126, "dur": 13.550, + "args": { + "External id": 1441367,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087888.512, "dur": 7.518, + "args": { + "External id": 1441368,"Record function id": 0, "Ev Idx": 6743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854087890.409, "dur": 5.013, + "args": { + "External id": 1441369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087892.138, "dur": 2.476, + "args": { + "External id": 1441370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854087893.070, "dur": 1.455, + "args": { + "External id": 1441371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087900.006, "dur": 6.590, + "args": { + "External id": 1441372,"Record function id": 0, "Sequence number": 15349009, "Fwd thread id": 1, "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854087901.457, "dur": 1.193, + "args": { + "External id": 1441373,"Sequence number": 15349009, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6748 + } + }, + { + "ph": "f", "id": 326, "pid": 2338706, "tid": 2379422, "ts": 6413854087901.457, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854087910.349, "dur": 519.374, + "args": { + "External id": 1441374,"Record function id": 0, "Sequence number": 15349008, "Fwd thread id": 1, "Ev Idx": 6749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854087925.830, "dur": 487.456, + "args": { + "External id": 1441375,"Sequence number": 15349008, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6750 + } + }, + { + "ph": "f", "id": 327, "pid": 2338706, "tid": 2379422, "ts": 6413854087925.830, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854087960.542, "dur": 8.657, + "args": { + "External id": 1441376,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854087965.799, "dur": 3.156, + "args": { + "External id": 1441377,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854087972.811, "dur": 25.801, + "args": { + "External id": 1441378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854087974.392, "dur": 23.380, + "args": { + "External id": 1441379,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854087976.352, "dur": 20.759, + "args": { + "External id": 1441380,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413854088003.489, "dur": 135.874, + "args": { + "External id": 1441381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 6756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088007.247, "dur": 9.443, + "args": { + "External id": 1441382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 6757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088008.181, "dur": 8.025, + "args": { + "External id": 1441383,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088009.892, "dur": 6.169, + "args": { + "External id": 1441384,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413854088018.018, "dur": 120.650, + "args": { + "External id": 1441385,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854088019.528, "dur": 117.585, + "args": { + "External id": 1441386,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 6761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854088145.717, "dur": 4.450, + "args": { + "External id": 1441387,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 6762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088147.982, "dur": 2.026, + "args": { + "External id": 1441388,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854088187.702, "dur": 5.078, + "args": { + "External id": 1441389,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854088194.470, "dur": 2.920, + "args": { + "External id": 1441390,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854088198.732, "dur": 2.386, + "args": { + "External id": 1441391,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088233.604, "dur": 2.637, + "args": { + "External id": 1441392,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088234.955, "dur": 1.124, + "args": { + "External id": 1441393,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413854088262.610, "dur": 129.465, + "args": { + "External id": 1441394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 6769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854088270.314, "dur": 6.605, + "args": { + "External id": 1441395,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088274.844, "dur": 1.064, + "args": { + "External id": 1441396,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854088278.699, "dur": 7.636, + "args": { + "External id": 1441397,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 6772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088282.786, "dur": 2.744, + "args": { + "External id": 1441398,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 6773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854088287.658, "dur": 3.228, + "args": { + "External id": 1441399,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088289.926, "dur": 0.636, + "args": { + "External id": 1441400,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854088291.848, "dur": 3.477, + "args": { + "External id": 1441401,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088294.163, "dur": 0.655, + "args": { + "External id": 1441402,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854088299.375, "dur": 5.440, + "args": { + "External id": 1441403,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 6778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088303.969, "dur": 0.476, + "args": { + "External id": 1441404,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 6779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088306.153, "dur": 6.830, + "args": { + "External id": 1441405,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 6780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854088310.866, "dur": 1.920, + "args": { + "External id": 1441406,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 6781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854088316.115, "dur": 2.749, + "args": { + "External id": 1441407,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 6782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088318.070, "dur": 0.446, + "args": { + "External id": 1441408,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 6783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088319.892, "dur": 2.676, + "args": { + "External id": 1441409,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088320.917, "dur": 1.555, + "args": { + "External id": 1441410,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 6785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854088323.655, "dur": 54.402, + "args": { + "External id": 1441411,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 6786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088380.317, "dur": 3.188, + "args": { + "External id": 1441412,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 6787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854088384.519, "dur": 3.572, + "args": { + "External id": 1441413,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 6788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088386.802, "dur": 0.480, + "args": { + "External id": 1441414,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 6789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088390.232, "dur": 0.798, + "args": { + "External id": 1441415,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 6790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854088442.197, "dur": 10.211, + "args": { + "External id": 1441416,"Record function id": 0, "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854088444.579, "dur": 7.019, + "args": { + "External id": 1441417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854088447.058, "dur": 3.563, + "args": { + "External id": 1441418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854088448.106, "dur": 2.407, + "args": { + "External id": 1441419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 6794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088456.484, "dur": 8.178, + "args": { + "External id": 1441420,"Record function id": 0, "Sequence number": 15349007, "Fwd thread id": 1, "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088457.692, "dur": 4.254, + "args": { + "External id": 1441421,"Sequence number": 15349007, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6796 + } + }, + { + "ph": "f", "id": 328, "pid": 2338706, "tid": 2379422, "ts": 6413854088457.692, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088459.531, "dur": 2.182, + "args": { + "External id": 1441422,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088460.693, "dur": 0.878, + "args": { + "External id": 1441423,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088468.381, "dur": 113.841, + "args": { + "External id": 1441424,"Record function id": 0, "Sequence number": 15349006, "Fwd thread id": 1, "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088469.368, "dur": 105.139, + "args": { + "External id": 1441425,"Sequence number": 15349006, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6800 + } + }, + { + "ph": "f", "id": 329, "pid": 2338706, "tid": 2379422, "ts": 6413854088469.368, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088474.555, "dur": 6.076, + "args": { + "External id": 1441426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088475.897, "dur": 4.229, + "args": { + "External id": 1441427,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088479.496, "dur": 0.492, + "args": { + "External id": 1441428,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854088481.802, "dur": 41.422, + "args": { + "External id": 1441429,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088524.510, "dur": 4.126, + "args": { + "External id": 1441430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088525.380, "dur": 2.687, + "args": { + "External id": 1441431,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088526.863, "dur": 1.066, + "args": { + "External id": 1441432,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088530.619, "dur": 5.612, + "args": { + "External id": 1441433,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088534.207, "dur": 1.433, + "args": { + "External id": 1441434,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088535.265, "dur": 0.295, + "args": { + "External id": 1441435,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854088536.717, "dur": 36.885, + "args": { + "External id": 1441436,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088587.264, "dur": 6.880, + "args": { + "External id": 1441437,"Record function id": 0, "Sequence number": 15349005, "Fwd thread id": 1, "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088588.413, "dur": 4.419, + "args": { + "External id": 1441438,"Sequence number": 15349005, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6813 + } + }, + { + "ph": "f", "id": 330, "pid": 2338706, "tid": 2379422, "ts": 6413854088588.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088590.091, "dur": 2.610, + "args": { + "External id": 1441439,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088591.381, "dur": 1.156, + "args": { + "External id": 1441440,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088597.548, "dur": 10.428, + "args": { + "External id": 1441441,"Record function id": 0, "Sequence number": 15349004, "Fwd thread id": 1, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088598.624, "dur": 6.623, + "args": { + "External id": 1441442,"Sequence number": 15349004, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6817 + } + }, + { + "ph": "f", "id": 331, "pid": 2338706, "tid": 2379422, "ts": 6413854088598.624, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088599.532, "dur": 5.512, + "args": { + "External id": 1441443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088602.728, "dur": 1.854, + "args": { + "External id": 1441444,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088603.888, "dur": 0.566, + "args": { + "External id": 1441445,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854088611.887, "dur": 4.721, + "args": { + "External id": 1441446,"Record function id": 0, "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854088613.122, "dur": 2.976, + "args": { + "External id": 1441447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854088614.184, "dur": 1.664, + "args": { + "External id": 1441448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854088614.649, "dur": 1.116, + "args": { + "External id": 1441449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088620.538, "dur": 6.924, + "args": { + "External id": 1441450,"Record function id": 0, "Sequence number": 15349003, "Fwd thread id": 1, "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088621.596, "dur": 2.928, + "args": { + "External id": 1441451,"Sequence number": 15349003, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 6826 + } + }, + { + "ph": "f", "id": 332, "pid": 2338706, "tid": 2379422, "ts": 6413854088621.596, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088622.584, "dur": 1.803, + "args": { + "External id": 1441452,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088623.365, "dur": 0.879, + "args": { + "External id": 1441453,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 6828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088630.739, "dur": 102.884, + "args": { + "External id": 1441454,"Record function id": 0, "Sequence number": 15349002, "Fwd thread id": 1, "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088634.013, "dur": 85.691, + "args": { + "External id": 1441455,"Sequence number": 15349002, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6830 + } + }, + { + "ph": "f", "id": 333, "pid": 2338706, "tid": 2379422, "ts": 6413854088634.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088637.011, "dur": 2.908, + "args": { + "External id": 1441456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088637.730, "dur": 1.726, + "args": { + "External id": 1441457,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088638.910, "dur": 0.450, + "args": { + "External id": 1441458,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 6833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854088640.605, "dur": 32.473, + "args": { + "External id": 1441459,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 6834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088674.220, "dur": 5.795, + "args": { + "External id": 1441460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088675.008, "dur": 4.454, + "args": { + "External id": 1441461,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 6836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088678.531, "dur": 0.818, + "args": { + "External id": 1441462,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 6837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088681.093, "dur": 6.742, + "args": { + "External id": 1441463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088682.908, "dur": 4.503, + "args": { + "External id": 1441464,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088684.695, "dur": 2.636, + "args": { + "External id": 1441465,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854088688.255, "dur": 30.767, + "args": { + "External id": 1441466,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 6841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088738.409, "dur": 33.938, + "args": { + "External id": 1441467,"Record function id": 0, "Sequence number": 15349001, "Fwd thread id": 1, "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088739.461, "dur": 4.814, + "args": { + "External id": 1441468,"Sequence number": 15349001, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6843 + } + }, + { + "ph": "f", "id": 334, "pid": 2338706, "tid": 2379422, "ts": 6413854088739.461, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088741.724, "dur": 2.398, + "args": { + "External id": 1441469,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088742.937, "dur": 1.080, + "args": { + "External id": 1441470,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854088746.980, "dur": 22.176, + "args": { + "External id": 1441471,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088776.096, "dur": 11.026, + "args": { + "External id": 1441472,"Record function id": 0, "Sequence number": 15349000, "Fwd thread id": 1, "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854088778.948, "dur": 5.454, + "args": { + "External id": 1441473,"Sequence number": 15349000, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6848 + } + }, + { + "ph": "f", "id": 335, "pid": 2338706, "tid": 2379422, "ts": 6413854088778.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854088780.424, "dur": 3.754, + "args": { + "External id": 1441474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 6849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854088781.262, "dur": 2.394, + "args": { + "External id": 1441475,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854088782.941, "dur": 0.596, + "args": { + "External id": 1441476,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 6851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854088791.062, "dur": 4.945, + "args": { + "External id": 1441477,"Record function id": 0, "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854088792.740, "dur": 2.770, + "args": { + "External id": 1441478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854088793.482, "dur": 1.499, + "args": { + "External id": 1441479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854088793.843, "dur": 1.048, + "args": { + "External id": 1441480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 6855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854088800.317, "dur": 534.223, + "args": { + "External id": 1441481,"Record function id": 0, "Sequence number": 15348999, "Fwd thread id": 1, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854088801.673, "dur": 491.209, + "args": { + "External id": 1441482,"Sequence number": 15348999, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 6857 + } + }, + { + "ph": "f", "id": 336, "pid": 2338706, "tid": 2379422, "ts": 6413854088801.673, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413854088823.821, "dur": 55.551, + "args": { + "External id": 1441483,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854088825.269, "dur": 53.834, + "args": { + "External id": 1441484,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854088828.271, "dur": 27.305, + "args": { + "External id": 1441485,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 6860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854088851.954, "dur": 2.977, + "args": { + "External id": 1441486,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854088856.896, "dur": 21.712, + "args": { + "External id": 1441487,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088894.340, "dur": 2.136, + "args": { + "External id": 1441488,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088895.188, "dur": 1.162, + "args": { + "External id": 1441489,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854088900.558, "dur": 3.539, + "args": { + "External id": 1441490,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854088901.250, "dur": 2.762, + "args": { + "External id": 1441491,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854088918.818, "dur": 2.648, + "args": { + "External id": 1441492,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854088932.151, "dur": 2.645, + "args": { + "External id": 1441493,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089169.129, "dur": 5.645, + "args": { + "External id": 1441494,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 6869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854089179.601, "dur": 36.772, + "args": { + "External id": 1441495,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 6870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089191.369, "dur": 1.148, + "args": { + "External id": 1441496,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 6871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854089222.689, "dur": 33.340, + "args": { + "External id": 1441497,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 6872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854089224.554, "dur": 31.263, + "args": { + "External id": 1441498,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 6873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089229.575, "dur": 4.945, + "args": { + "External id": 1441499,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854089238.767, "dur": 16.513, + "args": { + "External id": 1441500,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 6875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854089260.525, "dur": 2.813, + "args": { + "External id": 1441501,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 6876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089261.853, "dur": 1.374, + "args": { + "External id": 1441502,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 6877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089270.736, "dur": 2.511, + "args": { + "External id": 1441503,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089271.937, "dur": 1.203, + "args": { + "External id": 1441504,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089275.913, "dur": 4.248, + "args": { + "External id": 1441505,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089276.807, "dur": 3.257, + "args": { + "External id": 1441506,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854089314.545, "dur": 18.467, + "args": { + "External id": 1441507,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 6882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854089350.578, "dur": 10.680, + "args": { + "External id": 1441508,"Record function id": 0, "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854089353.867, "dur": 6.670, + "args": { + "External id": 1441509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854089356.521, "dur": 3.105, + "args": { + "External id": 1441510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854089357.526, "dur": 2.004, + "args": { + "External id": 1441511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 6886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089365.751, "dur": 8.447, + "args": { + "External id": 1441512,"Record function id": 0, "Sequence number": 15348998, "Fwd thread id": 1, "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089366.937, "dur": 4.274, + "args": { + "External id": 1441513,"Sequence number": 15348998, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6888 + } + }, + { + "ph": "f", "id": 337, "pid": 2338706, "tid": 2379422, "ts": 6413854089366.937, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089368.961, "dur": 2.015, + "args": { + "External id": 1441514,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089369.668, "dur": 1.160, + "args": { + "External id": 1441515,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089378.378, "dur": 150.431, + "args": { + "External id": 1441516,"Record function id": 0, "Sequence number": 15348997, "Fwd thread id": 1, "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089379.260, "dur": 141.614, + "args": { + "External id": 1441517,"Sequence number": 15348997, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6892 + } + }, + { + "ph": "f", "id": 338, "pid": 2338706, "tid": 2379422, "ts": 6413854089379.260, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854089387.266, "dur": 5.610, + "args": { + "External id": 1441518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854089389.087, "dur": 3.121, + "args": { + "External id": 1441519,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 6894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089391.121, "dur": 0.900, + "args": { + "External id": 1441520,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 6895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854089394.158, "dur": 74.084, + "args": { + "External id": 1441521,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 6896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854089469.082, "dur": 7.241, + "args": { + "External id": 1441522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854089469.749, "dur": 5.800, + "args": { + "External id": 1441523,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089474.402, "dur": 1.006, + "args": { + "External id": 1441524,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854089478.023, "dur": 3.926, + "args": { + "External id": 1441525,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854089479.806, "dur": 1.533, + "args": { + "External id": 1441526,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089480.883, "dur": 0.353, + "args": { + "External id": 1441527,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854089482.518, "dur": 37.614, + "args": { + "External id": 1441528,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 6903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089534.094, "dur": 12.929, + "args": { + "External id": 1441529,"Record function id": 0, "Sequence number": 15348996, "Fwd thread id": 1, "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089535.249, "dur": 8.589, + "args": { + "External id": 1441530,"Sequence number": 15348996, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6905 + } + }, + { + "ph": "f", "id": 339, "pid": 2338706, "tid": 2379422, "ts": 6413854089535.249, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089536.803, "dur": 6.851, + "args": { + "External id": 1441531,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089537.789, "dur": 5.683, + "args": { + "External id": 1441532,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089550.352, "dur": 11.098, + "args": { + "External id": 1441533,"Record function id": 0, "Sequence number": 15348995, "Fwd thread id": 1, "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089551.609, "dur": 7.328, + "args": { + "External id": 1441534,"Sequence number": 15348995, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6909 + } + }, + { + "ph": "f", "id": 340, "pid": 2338706, "tid": 2379422, "ts": 6413854089551.609, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854089552.564, "dur": 6.164, + "args": { + "External id": 1441535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854089553.323, "dur": 4.913, + "args": { + "External id": 1441536,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089557.542, "dur": 0.544, + "args": { + "External id": 1441537,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 6912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854089565.249, "dur": 5.459, + "args": { + "External id": 1441538,"Record function id": 0, "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854089567.308, "dur": 2.884, + "args": { + "External id": 1441539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854089568.297, "dur": 1.624, + "args": { + "External id": 1441540,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854089568.905, "dur": 0.900, + "args": { + "External id": 1441541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 6916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089574.263, "dur": 7.894, + "args": { + "External id": 1441542,"Record function id": 0, "Sequence number": 15348994, "Fwd thread id": 1, "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854089575.196, "dur": 3.586, + "args": { + "External id": 1441543,"Sequence number": 15348994, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 6918 + } + }, + { + "ph": "f", "id": 341, "pid": 2338706, "tid": 2379422, "ts": 6413854089575.196, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089576.660, "dur": 1.967, + "args": { + "External id": 1441544,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089577.450, "dur": 1.033, + "args": { + "External id": 1441545,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 6920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854089586.530, "dur": 435.254, + "args": { + "External id": 1441546,"Record function id": 0, "Sequence number": 15348993, "Fwd thread id": 1, "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854089587.965, "dur": 386.745, + "args": { + "External id": 1441547,"Sequence number": 15348993, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6922 + } + }, + { + "ph": "f", "id": 342, "pid": 2338706, "tid": 2379422, "ts": 6413854089587.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854089606.402, "dur": 7.115, + "args": { + "External id": 1441548,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089609.342, "dur": 3.710, + "args": { + "External id": 1441549,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854089615.684, "dur": 3.479, + "args": { + "External id": 1441550,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089617.349, "dur": 1.567, + "args": { + "External id": 1441551,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854089620.624, "dur": 4.547, + "args": { + "External id": 1441552,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089622.205, "dur": 2.772, + "args": { + "External id": 1441553,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854089650.727, "dur": 298.846, + "args": { + "External id": 1441554,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854089738.857, "dur": 3.220, + "args": { + "External id": 1441555,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854089744.889, "dur": 5.707, + "args": { + "External id": 1441556,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854089752.119, "dur": 2.556, + "args": { + "External id": 1441557,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854089756.005, "dur": 2.353, + "args": { + "External id": 1441558,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089845.810, "dur": 2.800, + "args": { + "External id": 1441559,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089847.024, "dur": 1.465, + "args": { + "External id": 1441560,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854089850.190, "dur": 26.955, + "args": { + "External id": 1441561,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089855.479, "dur": 2.517, + "args": { + "External id": 1441562,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854089881.378, "dur": 1.847, + "args": { + "External id": 1441563,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854089882.662, "dur": 0.475, + "args": { + "External id": 1441564,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854089884.646, "dur": 22.113, + "args": { + "External id": 1441565,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 6940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854089887.593, "dur": 0.385, + "args": { + "External id": 1441566,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 6941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854089962.224, "dur": 3.406, + "args": { + "External id": 1441567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854089968.713, "dur": 0.753, + "args": { + "External id": 1441568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854089971.360, "dur": 0.613, + "args": { + "External id": 1441569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854090032.370, "dur": 290.726, + "args": { + "External id": 1441570,"Record function id": 0, "Sequence number": 15348992, "Fwd thread id": 1, "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854090034.512, "dur": 280.848, + "args": { + "External id": 1441571,"Sequence number": 15348992, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6946 + } + }, + { + "ph": "f", "id": 343, "pid": 2338706, "tid": 2379422, "ts": 6413854090034.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854090094.208, "dur": 55.814, + "args": { + "External id": 1441572,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090098.070, "dur": 5.112, + "args": { + "External id": 1441573,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854090104.702, "dur": 44.699, + "args": { + "External id": 1441574,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 6949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854090163.207, "dur": 5.428, + "args": { + "External id": 1441575,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 6950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090165.904, "dur": 2.377, + "args": { + "External id": 1441576,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854090332.606, "dur": 197.642, + "args": { + "External id": 1441577,"Record function id": 0, "Sequence number": 15348991, "Fwd thread id": 1, "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854090334.462, "dur": 188.596, + "args": { + "External id": 1441578,"Sequence number": 15348991, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6953 + } + }, + { + "ph": "f", "id": 344, "pid": 2338706, "tid": 2379422, "ts": 6413854090334.462, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854090347.218, "dur": 66.626, + "args": { + "External id": 1441579,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090355.015, "dur": 5.164, + "args": { + "External id": 1441580,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854090376.208, "dur": 36.936, + "args": { + "External id": 1441581,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 6956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854090421.699, "dur": 5.945, + "args": { + "External id": 1441582,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 6957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090424.516, "dur": 2.815, + "args": { + "External id": 1441583,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090536.598, "dur": 15.709, + "args": { + "External id": 1441584,"Record function id": 0, "Sequence number": 15348990, "Fwd thread id": 1, "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090537.987, "dur": 10.777, + "args": { + "External id": 1441585,"Sequence number": 15348990, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6960 + } + }, + { + "ph": "f", "id": 345, "pid": 2338706, "tid": 2379422, "ts": 6413854090537.987, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090540.745, "dur": 7.759, + "args": { + "External id": 1441586,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090542.215, "dur": 6.096, + "args": { + "External id": 1441587,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090556.191, "dur": 8.189, + "args": { + "External id": 1441588,"Record function id": 0, "Sequence number": 15348989, "Fwd thread id": 1, "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090557.419, "dur": 3.815, + "args": { + "External id": 1441589,"Sequence number": 15348989, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 6964 + } + }, + { + "ph": "f", "id": 346, "pid": 2338706, "tid": 2379422, "ts": 6413854090557.419, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090559.242, "dur": 1.865, + "args": { + "External id": 1441590,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090560.085, "dur": 0.873, + "args": { + "External id": 1441591,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 6966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090567.913, "dur": 9.653, + "args": { + "External id": 1441592,"Record function id": 0, "Sequence number": 15348988, "Fwd thread id": 1, "Ev Idx": 6967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090568.569, "dur": 6.014, + "args": { + "External id": 1441593,"Sequence number": 15348988, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 6968 + } + }, + { + "ph": "f", "id": 347, "pid": 2338706, "tid": 2379422, "ts": 6413854090568.569, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090570.226, "dur": 4.200, + "args": { + "External id": 1441594,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090573.085, "dur": 1.233, + "args": { + "External id": 1441595,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 6970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090581.592, "dur": 9.297, + "args": { + "External id": 1441596,"Record function id": 0, "Sequence number": 15348987, "Fwd thread id": 1, "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090583.218, "dur": 3.368, + "args": { + "External id": 1441597,"Sequence number": 15348987, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 6972 + } + }, + { + "ph": "f", "id": 348, "pid": 2338706, "tid": 2379422, "ts": 6413854090583.218, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090584.796, "dur": 1.652, + "args": { + "External id": 1441598,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090585.530, "dur": 0.826, + "args": { + "External id": 1441599,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 6974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090594.579, "dur": 176.014, + "args": { + "External id": 1441600,"Record function id": 0, "Sequence number": 15348986, "Fwd thread id": 1, "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090595.353, "dur": 166.605, + "args": { + "External id": 1441601,"Sequence number": 15348986, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6976 + } + }, + { + "ph": "f", "id": 349, "pid": 2338706, "tid": 2379422, "ts": 6413854090595.353, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090600.330, "dur": 10.009, + "args": { + "External id": 1441602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 6977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090605.098, "dur": 4.506, + "args": { + "External id": 1441603,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 6978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090607.582, "dur": 1.692, + "args": { + "External id": 1441604,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 6979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854090611.895, "dur": 69.571, + "args": { + "External id": 1441605,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 6980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090682.720, "dur": 6.978, + "args": { + "External id": 1441606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090683.686, "dur": 5.268, + "args": { + "External id": 1441607,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 6982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090685.362, "dur": 3.446, + "args": { + "External id": 1441608,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090691.790, "dur": 7.168, + "args": { + "External id": 1441609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090696.451, "dur": 1.803, + "args": { + "External id": 1441610,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090697.740, "dur": 0.387, + "args": { + "External id": 1441611,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854090699.577, "dur": 61.598, + "args": { + "External id": 1441612,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 6987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090775.882, "dur": 7.459, + "args": { + "External id": 1441613,"Record function id": 0, "Sequence number": 15348985, "Fwd thread id": 1, "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090776.928, "dur": 4.690, + "args": { + "External id": 1441614,"Sequence number": 15348985, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 6989 + } + }, + { + "ph": "f", "id": 350, "pid": 2338706, "tid": 2379422, "ts": 6413854090776.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090778.858, "dur": 2.622, + "args": { + "External id": 1441615,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090779.915, "dur": 1.458, + "args": { + "External id": 1441616,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 6991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090786.717, "dur": 10.262, + "args": { + "External id": 1441617,"Record function id": 0, "Sequence number": 15348984, "Fwd thread id": 1, "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090787.712, "dur": 6.796, + "args": { + "External id": 1441618,"Sequence number": 15348984, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6993 + } + }, + { + "ph": "f", "id": 351, "pid": 2338706, "tid": 2379422, "ts": 6413854090787.712, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090788.833, "dur": 5.463, + "args": { + "External id": 1441619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 6994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090789.493, "dur": 4.312, + "args": { + "External id": 1441620,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 6995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090792.940, "dur": 0.738, + "args": { + "External id": 1441621,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 6996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854090802.693, "dur": 9.512, + "args": { + "External id": 1441622,"Record function id": 0, "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854090804.794, "dur": 6.566, + "args": { + "External id": 1441623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854090807.154, "dur": 3.878, + "args": { + "External id": 1441624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 6999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854090808.307, "dur": 2.643, + "args": { + "External id": 1441625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090815.487, "dur": 7.002, + "args": { + "External id": 1441626,"Record function id": 0, "Sequence number": 15348983, "Fwd thread id": 1, "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090816.696, "dur": 2.982, + "args": { + "External id": 1441627,"Sequence number": 15348983, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 7002 + } + }, + { + "ph": "f", "id": 352, "pid": 2338706, "tid": 2379422, "ts": 6413854090816.696, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090817.905, "dur": 1.617, + "args": { + "External id": 1441628,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090818.625, "dur": 0.765, + "args": { + "External id": 1441629,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090825.696, "dur": 112.679, + "args": { + "External id": 1441630,"Record function id": 0, "Sequence number": 15348982, "Fwd thread id": 1, "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090828.948, "dur": 101.092, + "args": { + "External id": 1441631,"Sequence number": 15348982, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7006 + } + }, + { + "ph": "f", "id": 353, "pid": 2338706, "tid": 2379422, "ts": 6413854090828.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090832.359, "dur": 2.696, + "args": { + "External id": 1441632,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090832.822, "dur": 1.789, + "args": { + "External id": 1441633,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090833.920, "dur": 0.575, + "args": { + "External id": 1441634,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 7009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854090835.635, "dur": 28.153, + "args": { + "External id": 1441635,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 7010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090864.785, "dur": 6.055, + "args": { + "External id": 1441636,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090865.491, "dur": 4.733, + "args": { + "External id": 1441637,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090869.245, "dur": 0.864, + "args": { + "External id": 1441638,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854090872.197, "dur": 4.941, + "args": { + "External id": 1441639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854090874.192, "dur": 2.263, + "args": { + "External id": 1441640,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854090875.966, "dur": 0.424, + "args": { + "External id": 1441641,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854090877.654, "dur": 51.686, + "args": { + "External id": 1441642,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 7017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090943.097, "dur": 30.007, + "args": { + "External id": 1441643,"Record function id": 0, "Sequence number": 15348981, "Fwd thread id": 1, "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090944.227, "dur": 4.448, + "args": { + "External id": 1441644,"Sequence number": 15348981, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7019 + } + }, + { + "ph": "f", "id": 354, "pid": 2338706, "tid": 2379422, "ts": 6413854090944.227, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854090946.303, "dur": 2.214, + "args": { + "External id": 1441645,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854090947.281, "dur": 1.107, + "args": { + "External id": 1441646,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854090951.833, "dur": 19.201, + "args": { + "External id": 1441647,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854090999.929, "dur": 10.815, + "args": { + "External id": 1441648,"Record function id": 0, "Sequence number": 15348980, "Fwd thread id": 1, "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091001.761, "dur": 6.286, + "args": { + "External id": 1441649,"Sequence number": 15348980, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7024 + } + }, + { + "ph": "f", "id": 355, "pid": 2338706, "tid": 2379422, "ts": 6413854091001.761, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091003.035, "dur": 4.750, + "args": { + "External id": 1441650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091004.221, "dur": 2.810, + "args": { + "External id": 1441651,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091006.010, "dur": 0.755, + "args": { + "External id": 1441652,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854091016.093, "dur": 8.003, + "args": { + "External id": 1441653,"Record function id": 0, "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854091017.601, "dur": 6.007, + "args": { + "External id": 1441654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854091018.963, "dur": 4.195, + "args": { + "External id": 1441655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854091019.488, "dur": 3.577, + "args": { + "External id": 1441656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091027.467, "dur": 10.588, + "args": { + "External id": 1441657,"Record function id": 0, "Sequence number": 15348979, "Fwd thread id": 1, "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091028.659, "dur": 6.059, + "args": { + "External id": 1441658,"Sequence number": 15348979, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7033 + } + }, + { + "ph": "f", "id": 356, "pid": 2338706, "tid": 2379422, "ts": 6413854091028.659, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091030.196, "dur": 4.375, + "args": { + "External id": 1441659,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091033.362, "dur": 1.120, + "args": { + "External id": 1441660,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091041.357, "dur": 152.474, + "args": { + "External id": 1441661,"Record function id": 0, "Sequence number": 15348978, "Fwd thread id": 1, "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091042.235, "dur": 139.461, + "args": { + "External id": 1441662,"Sequence number": 15348978, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7037 + } + }, + { + "ph": "f", "id": 357, "pid": 2338706, "tid": 2379422, "ts": 6413854091042.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091045.586, "dur": 2.747, + "args": { + "External id": 1441663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091046.215, "dur": 1.656, + "args": { + "External id": 1441664,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 7039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091047.345, "dur": 0.416, + "args": { + "External id": 1441665,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854091049.205, "dur": 79.642, + "args": { + "External id": 1441666,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091133.963, "dur": 4.810, + "args": { + "External id": 1441667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091135.320, "dur": 2.602, + "args": { + "External id": 1441668,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091136.993, "dur": 0.813, + "args": { + "External id": 1441669,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091140.254, "dur": 4.505, + "args": { + "External id": 1441670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091141.966, "dur": 2.255, + "args": { + "External id": 1441671,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091143.457, "dur": 0.700, + "args": { + "External id": 1441672,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854091147.317, "dur": 33.643, + "args": { + "External id": 1441673,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 7048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091200.038, "dur": 26.980, + "args": { + "External id": 1441674,"Record function id": 0, "Sequence number": 15348977, "Fwd thread id": 1, "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091201.034, "dur": 4.537, + "args": { + "External id": 1441675,"Sequence number": 15348977, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7050 + } + }, + { + "ph": "f", "id": 358, "pid": 2338706, "tid": 2379422, "ts": 6413854091201.034, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091202.985, "dur": 2.436, + "args": { + "External id": 1441676,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091204.056, "dur": 1.198, + "args": { + "External id": 1441677,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854091208.493, "dur": 16.232, + "args": { + "External id": 1441678,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091230.674, "dur": 10.471, + "args": { + "External id": 1441679,"Record function id": 0, "Sequence number": 15348976, "Fwd thread id": 1, "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091231.430, "dur": 7.605, + "args": { + "External id": 1441680,"Sequence number": 15348976, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7055 + } + }, + { + "ph": "f", "id": 359, "pid": 2338706, "tid": 2379422, "ts": 6413854091231.430, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091232.549, "dur": 6.302, + "args": { + "External id": 1441681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091233.258, "dur": 5.029, + "args": { + "External id": 1441682,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091235.304, "dur": 2.884, + "args": { + "External id": 1441683,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854091245.401, "dur": 7.012, + "args": { + "External id": 1441684,"Record function id": 0, "Ev Idx": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854091246.918, "dur": 5.018, + "args": { + "External id": 1441685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854091248.227, "dur": 2.537, + "args": { + "External id": 1441686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854091249.152, "dur": 1.506, + "args": { + "External id": 1441687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854091257.320, "dur": 355.974, + "args": { + "External id": 1441688,"Record function id": 0, "Sequence number": 15348975, "Fwd thread id": 1, "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854091258.877, "dur": 328.765, + "args": { + "External id": 1441689,"Sequence number": 15348975, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7064 + } + }, + { + "ph": "f", "id": 360, "pid": 2338706, "tid": 2379422, "ts": 6413854091258.877, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091299.219, "dur": 2.220, + "args": { + "External id": 1441690,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091300.245, "dur": 1.054, + "args": { + "External id": 1441691,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854091316.848, "dur": 4.082, + "args": { + "External id": 1441692,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854091330.829, "dur": 2.004, + "args": { + "External id": 1441693,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091482.743, "dur": 2.037, + "args": { + "External id": 1441694,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854091488.926, "dur": 36.051, + "args": { + "External id": 1441695,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 7070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091502.222, "dur": 0.845, + "args": { + "External id": 1441696,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 7071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854091530.288, "dur": 30.521, + "args": { + "External id": 1441697,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 7072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854091534.776, "dur": 25.824, + "args": { + "External id": 1441698,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 7073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091539.034, "dur": 4.206, + "args": { + "External id": 1441699,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854091544.869, "dur": 15.135, + "args": { + "External id": 1441700,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 7075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854091565.192, "dur": 5.275, + "args": { + "External id": 1441701,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 7076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091566.706, "dur": 3.628, + "args": { + "External id": 1441702,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 7077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091576.527, "dur": 4.339, + "args": { + "External id": 1441703,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091579.861, "dur": 0.921, + "args": { + "External id": 1441704,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854091596.472, "dur": 13.439, + "args": { + "External id": 1441705,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854091621.899, "dur": 8.177, + "args": { + "External id": 1441706,"Record function id": 0, "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854091624.234, "dur": 5.291, + "args": { + "External id": 1441707,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854091626.208, "dur": 2.127, + "args": { + "External id": 1441708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854091626.812, "dur": 1.448, + "args": { + "External id": 1441709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091634.383, "dur": 7.620, + "args": { + "External id": 1441710,"Record function id": 0, "Sequence number": 15348974, "Fwd thread id": 1, "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854091636.200, "dur": 0.994, + "args": { + "External id": 1441711,"Sequence number": 15348974, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7086 + } + }, + { + "ph": "f", "id": 361, "pid": 2338706, "tid": 2379422, "ts": 6413854091636.200, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854091645.956, "dur": 458.798, + "args": { + "External id": 1441712,"Record function id": 0, "Sequence number": 15348973, "Fwd thread id": 1, "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854091647.481, "dur": 439.775, + "args": { + "External id": 1441713,"Sequence number": 15348973, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7088 + } + }, + { + "ph": "f", "id": 362, "pid": 2338706, "tid": 2379422, "ts": 6413854091647.481, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091679.746, "dur": 8.330, + "args": { + "External id": 1441714,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854091685.050, "dur": 2.793, + "args": { + "External id": 1441715,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]", "[16384, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[67108864, 16384, 1], [], []], "Input Dims": [[8, 4096, 4096], [], []], "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091691.690, "dur": 4.498, + "args": { + "External id": 1441716,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091693.059, "dur": 2.603, + "args": { + "External id": 1441717,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091694.912, "dur": 0.616, + "args": { + "External id": 1441718,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2379422, + "ts": 6413854091699.746, "dur": 77.079, + "args": { + "External id": 1441719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16384, 1], [1, 14336], []], "Input Dims": [[32768, 4096], [14336, 4096], []], "Ev Idx": 7094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854091702.988, "dur": 3.462, + "args": { + "External id": 1441720,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 14336]], "Input Dims": [[14336, 4096]], "Ev Idx": 7095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854091703.551, "dur": 2.410, + "args": { + "External id": 1441721,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 14336], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 7096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091704.968, "dur": 0.880, + "args": { + "External id": 1441722,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[14336, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 14336], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 7097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2379422, + "ts": 6413854091707.530, "dur": 68.824, + "args": { + "External id": 1441723,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 7098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854091708.856, "dur": 66.610, + "args": { + "External id": 1441724,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16384, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 7099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854091780.503, "dur": 3.007, + "args": { + "External id": 1441725,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [58720256, 14336, 1]], "Input Dims": [[32768, 14336], [8, 4096, 14336]], "Ev Idx": 7100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091782.092, "dur": 1.286, + "args": { + "External id": 1441726,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 7101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854091816.616, "dur": 3.483, + "args": { + "External id": 1441727,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854091821.504, "dur": 5.251, + "args": { + "External id": 1441728,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854091828.002, "dur": 2.422, + "args": { + "External id": 1441729,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091859.705, "dur": 1.999, + "args": { + "External id": 1441730,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091860.520, "dur": 1.041, + "args": { + "External id": 1441731,"Record function id": 0, "Concrete Inputs": ["", "[-1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 2338706, "tid": 2379422, + "ts": 6413854091886.186, "dur": 143.206, + "args": { + "External id": 1441732,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[16384, 1], [14336, 1]], []], "Input Dims": [[], [[32768, 4096], [32768, 14336]], []], "Ev Idx": 7107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854091893.854, "dur": 5.689, + "args": { + "External id": 1441733,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091897.526, "dur": 1.264, + "args": { + "External id": 1441734,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096, 1]", "[16384, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854091901.123, "dur": 5.685, + "args": { + "External id": 1441735,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16384, 1, 1], []], "Input Dims": [[32768, 4096, 1], []], "Ev Idx": 7110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091904.929, "dur": 0.585, + "args": { + "External id": 1441736,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 32768]", "[1, 1, 16384]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[16384, 1, 1], [], [], []], "Input Dims": [[32768, 4096, 1], [], [], []], "Ev Idx": 7111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2379422, + "ts": 6413854091908.140, "dur": 2.981, + "args": { + "External id": 1441737,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 7112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091910.250, "dur": 0.477, + "args": { + "External id": 1441738,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 7113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854091911.949, "dur": 3.400, + "args": { + "External id": 1441739,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 7114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091913.973, "dur": 0.591, + "args": { + "External id": 1441740,"Record function id": 0, "Concrete Inputs": ["", "[1, 14336, 32768]", "[1, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1, 1], [], [], []], "Input Dims": [[32768, 14336, 1], [], [], []], "Ev Idx": 7115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854091919.535, "dur": 5.200, + "args": { + "External id": 1441741,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 16384], []], "Input Dims": [[4096, 1, 32768], []], "Ev Idx": 7116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091923.630, "dur": 0.780, + "args": { + "External id": 1441742,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768, 1]", "[1, 16384, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 16384], [], [], []], "Input Dims": [[4096, 1, 32768], [], [], []], "Ev Idx": 7117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091925.820, "dur": 8.115, + "args": { + "External id": 1441743,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 16384, 1], []], "Input Dims": [[4096, 32768, 1], []], "Ev Idx": 7118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854091929.508, "dur": 4.252, + "args": { + "External id": 1441744,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096, 32768]", "[4096, 1, 16384]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 16384, 1], [], []], "Input Dims": [[4096, 32768, 1], [], []], "Ev Idx": 7119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854091935.208, "dur": 3.382, + "args": { + "External id": 1441745,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 14336], []], "Input Dims": [[1, 14336, 32768], []], "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854091937.558, "dur": 0.706, + "args": { + "External id": 1441746,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336, 1]", "[14336, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 14336], [], [], []], "Input Dims": [[1, 14336, 32768], [], [], []], "Ev Idx": 7121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854091941.489, "dur": 3.294, + "args": { + "External id": 1441747,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 7122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854091942.479, "dur": 2.207, + "args": { + "External id": 1441748,"Record function id": 0, "Concrete Inputs": ["", "[1, 32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 1], []], "Input Dims": [[32768, 14336, 1], []], "Ev Idx": 7123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854091945.961, "dur": 69.283, + "args": { + "External id": 1441749,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1, 16384], [469762048, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336]], "Ev Idx": 7124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092018.745, "dur": 1.632, + "args": { + "External id": 1441750,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[1, 4096, 14336], []], "Ev Idx": 7125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 2338706, "tid": 2379422, + "ts": 6413854092021.417, "dur": 3.580, + "args": { + "External id": 1441751,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 14336, 1], []], "Input Dims": [[4096, 1, 14336], []], "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092023.441, "dur": 0.588, + "args": { + "External id": 1441752,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336, 1]", "[14336, 1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 14336, 1], [], [], []], "Input Dims": [[4096, 1, 14336], [], [], []], "Ev Idx": 7127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092027.221, "dur": 1.150, + "args": { + "External id": 1441753,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1, 14336], []], "Input Dims": [[4096, 14336, 1], []], "Ev Idx": 7128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854092117.306, "dur": 9.842, + "args": { + "External id": 1441754,"Record function id": 0, "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854092119.399, "dur": 7.049, + "args": { + "External id": 1441755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854092121.920, "dur": 3.383, + "args": { + "External id": 1441756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854092122.779, "dur": 2.432, + "args": { + "External id": 1441757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092131.425, "dur": 9.019, + "args": { + "External id": 1441758,"Record function id": 0, "Sequence number": 15348972, "Fwd thread id": 1, "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092132.659, "dur": 4.567, + "args": { + "External id": 1441759,"Sequence number": 15348972, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 7134 + } + }, + { + "ph": "f", "id": 363, "pid": 2338706, "tid": 2379422, "ts": 6413854092132.659, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854092134.761, "dur": 2.169, + "args": { + "External id": 1441760,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092135.678, "dur": 1.104, + "args": { + "External id": 1441761,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092144.171, "dur": 119.577, + "args": { + "External id": 1441762,"Record function id": 0, "Sequence number": 15348971, "Fwd thread id": 1, "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092145.459, "dur": 110.777, + "args": { + "External id": 1441763,"Sequence number": 15348971, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7138 + } + }, + { + "ph": "f", "id": 364, "pid": 2338706, "tid": 2379422, "ts": 6413854092145.459, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092148.999, "dur": 9.425, + "args": { + "External id": 1441764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092150.394, "dur": 7.438, + "args": { + "External id": 1441765,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 7140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092154.364, "dur": 3.325, + "args": { + "External id": 1441766,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854092159.560, "dur": 47.808, + "args": { + "External id": 1441767,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092208.546, "dur": 4.083, + "args": { + "External id": 1441768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092209.381, "dur": 2.695, + "args": { + "External id": 1441769,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 7144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092211.168, "dur": 0.725, + "args": { + "External id": 1441770,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 7145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092214.355, "dur": 6.430, + "args": { + "External id": 1441771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092216.084, "dur": 4.182, + "args": { + "External id": 1441772,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092219.464, "dur": 0.736, + "args": { + "External id": 1441773,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854092221.654, "dur": 33.931, + "args": { + "External id": 1441774,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 7149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092268.977, "dur": 6.951, + "args": { + "External id": 1441775,"Record function id": 0, "Sequence number": 15348970, "Fwd thread id": 1, "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092270.058, "dur": 4.452, + "args": { + "External id": 1441776,"Sequence number": 15348970, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7151 + } + }, + { + "ph": "f", "id": 365, "pid": 2338706, "tid": 2379422, "ts": 6413854092270.058, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854092271.828, "dur": 2.532, + "args": { + "External id": 1441777,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092273.001, "dur": 1.217, + "args": { + "External id": 1441778,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092279.504, "dur": 9.187, + "args": { + "External id": 1441779,"Record function id": 0, "Sequence number": 15348969, "Fwd thread id": 1, "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092280.340, "dur": 6.527, + "args": { + "External id": 1441780,"Sequence number": 15348969, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7155 + } + }, + { + "ph": "f", "id": 366, "pid": 2338706, "tid": 2379422, "ts": 6413854092280.340, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092281.533, "dur": 5.102, + "args": { + "External id": 1441781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092282.187, "dur": 3.964, + "args": { + "External id": 1441782,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092285.583, "dur": 0.397, + "args": { + "External id": 1441783,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854092292.895, "dur": 8.193, + "args": { + "External id": 1441784,"Record function id": 0, "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854092294.361, "dur": 6.190, + "args": { + "External id": 1441785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854092295.661, "dur": 4.608, + "args": { + "External id": 1441786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854092296.513, "dur": 3.672, + "args": { + "External id": 1441787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092304.642, "dur": 7.014, + "args": { + "External id": 1441788,"Record function id": 0, "Sequence number": 15348968, "Fwd thread id": 1, "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092305.675, "dur": 3.745, + "args": { + "External id": 1441789,"Sequence number": 15348968, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[58720256, 14336, 1]], "Input Dims": [[8, 4096, 14336]], "Ev Idx": 7164 + } + }, + { + "ph": "f", "id": 367, "pid": 2338706, "tid": 2379422, "ts": 6413854092305.675, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854092306.875, "dur": 2.386, + "args": { + "External id": 1441790,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092308.121, "dur": 1.010, + "args": { + "External id": 1441791,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092315.195, "dur": 215.478, + "args": { + "External id": 1441792,"Record function id": 0, "Sequence number": 15348967, "Fwd thread id": 1, "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092428.591, "dur": 92.858, + "args": { + "External id": 1441793,"Sequence number": 15348967, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7168 + } + }, + { + "ph": "f", "id": 368, "pid": 2338706, "tid": 2379422, "ts": 6413854092428.591, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092432.232, "dur": 3.360, + "args": { + "External id": 1441794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[32768, 14336]], "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092432.878, "dur": 2.173, + "args": { + "External id": 1441795,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[32768, 14336], [], []], "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092434.315, "dur": 0.580, + "args": { + "External id": 1441796,"Record function id": 0, "Concrete Inputs": ["", "[14336, 32768]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[32768, 14336], [], [], []], "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854092436.337, "dur": 37.272, + "args": { + "External id": 1441797,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096]], "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092474.944, "dur": 6.933, + "args": { + "External id": 1441798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092475.489, "dur": 5.858, + "args": { + "External id": 1441799,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 7174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092478.688, "dur": 2.492, + "args": { + "External id": 1441800,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 7175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092483.613, "dur": 4.591, + "args": { + "External id": 1441801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092485.562, "dur": 2.227, + "args": { + "External id": 1441802,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092487.184, "dur": 0.510, + "args": { + "External id": 1441803,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854092488.703, "dur": 31.990, + "args": { + "External id": 1441804,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 7179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092536.049, "dur": 36.663, + "args": { + "External id": 1441805,"Record function id": 0, "Sequence number": 15348966, "Fwd thread id": 1, "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092537.007, "dur": 4.115, + "args": { + "External id": 1441806,"Sequence number": 15348966, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7181 + } + }, + { + "ph": "f", "id": 369, "pid": 2338706, "tid": 2379422, "ts": 6413854092537.007, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854092538.769, "dur": 2.207, + "args": { + "External id": 1441807,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092539.529, "dur": 1.307, + "args": { + "External id": 1441808,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854092544.174, "dur": 25.218, + "args": { + "External id": 1441809,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092576.576, "dur": 11.205, + "args": { + "External id": 1441810,"Record function id": 0, "Sequence number": 15348965, "Fwd thread id": 1, "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854092579.957, "dur": 4.707, + "args": { + "External id": 1441811,"Sequence number": 15348965, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7186 + } + }, + { + "ph": "f", "id": 370, "pid": 2338706, "tid": 2379422, "ts": 6413854092579.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854092580.923, "dur": 3.519, + "args": { + "External id": 1441812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 14336]], "Ev Idx": 7187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854092581.654, "dur": 2.177, + "args": { + "External id": 1441813,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 7188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092583.212, "dur": 0.480, + "args": { + "External id": 1441814,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 7189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854092591.943, "dur": 4.680, + "args": { + "External id": 1441815,"Record function id": 0, "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854092593.361, "dur": 2.784, + "args": { + "External id": 1441816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854092594.120, "dur": 1.537, + "args": { + "External id": 1441817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854092594.536, "dur": 1.028, + "args": { + "External id": 1441818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854092600.968, "dur": 506.804, + "args": { + "External id": 1441819,"Record function id": 0, "Sequence number": 15348964, "Fwd thread id": 1, "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854092610.644, "dur": 418.389, + "args": { + "External id": 1441820,"Sequence number": 15348964, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 7195 + } + }, + { + "ph": "f", "id": 371, "pid": 2338706, "tid": 2379422, "ts": 6413854092610.644, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2379422, + "ts": 6413854092639.204, "dur": 34.858, + "args": { + "External id": 1441821,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854092640.857, "dur": 33.015, + "args": { + "External id": 1441822,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854092643.762, "dur": 6.689, + "args": { + "External id": 1441823,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], [], []], "Ev Idx": 7198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854092646.722, "dur": 3.137, + "args": { + "External id": 1441824,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854092651.676, "dur": 21.704, + "args": { + "External id": 1441825,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854092689.884, "dur": 1.965, + "args": { + "External id": 1441826,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092690.384, "dur": 1.323, + "args": { + "External id": 1441827,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854092695.795, "dur": 1.365, + "args": { + "External id": 1441828,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092696.178, "dur": 0.889, + "args": { + "External id": 1441829,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854092712.237, "dur": 2.834, + "args": { + "External id": 1441830,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854092726.480, "dur": 2.101, + "args": { + "External id": 1441831,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092893.966, "dur": 5.733, + "args": { + "External id": 1441832,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 7207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854092904.228, "dur": 30.808, + "args": { + "External id": 1441833,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 7208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092913.762, "dur": 0.770, + "args": { + "External id": 1441834,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 7209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854092941.333, "dur": 31.098, + "args": { + "External id": 1441835,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 7210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854092943.453, "dur": 28.767, + "args": { + "External id": 1441836,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 7211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854092948.597, "dur": 4.422, + "args": { + "External id": 1441837,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854092957.566, "dur": 14.099, + "args": { + "External id": 1441838,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 7213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854092996.287, "dur": 3.940, + "args": { + "External id": 1441839,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 7214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854092998.308, "dur": 1.657, + "args": { + "External id": 1441840,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 7215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093008.735, "dur": 3.135, + "args": { + "External id": 1441841,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093010.118, "dur": 1.649, + "args": { + "External id": 1441842,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093014.117, "dur": 1.891, + "args": { + "External id": 1441843,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093014.856, "dur": 1.057, + "args": { + "External id": 1441844,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854093050.809, "dur": 54.062, + "args": { + "External id": 1441845,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854093124.943, "dur": 11.286, + "args": { + "External id": 1441846,"Record function id": 0, "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854093128.135, "dur": 7.281, + "args": { + "External id": 1441847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854093130.935, "dur": 3.593, + "args": { + "External id": 1441848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854093131.963, "dur": 2.462, + "args": { + "External id": 1441849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093140.210, "dur": 9.558, + "args": { + "External id": 1441850,"Record function id": 0, "Sequence number": 15348963, "Fwd thread id": 1, "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093141.601, "dur": 4.882, + "args": { + "External id": 1441851,"Sequence number": 15348963, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7226 + } + }, + { + "ph": "f", "id": 372, "pid": 2338706, "tid": 2379422, "ts": 6413854093141.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093143.879, "dur": 2.373, + "args": { + "External id": 1441852,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093144.541, "dur": 1.595, + "args": { + "External id": 1441853,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093154.020, "dur": 158.053, + "args": { + "External id": 1441854,"Record function id": 0, "Sequence number": 15348962, "Fwd thread id": 1, "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093154.912, "dur": 149.011, + "args": { + "External id": 1441855,"Sequence number": 15348962, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7230 + } + }, + { + "ph": "f", "id": 373, "pid": 2338706, "tid": 2379422, "ts": 6413854093154.912, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854093160.346, "dur": 8.984, + "args": { + "External id": 1441856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854093164.809, "dur": 3.787, + "args": { + "External id": 1441857,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 7232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093167.210, "dur": 1.077, + "args": { + "External id": 1441858,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854093171.006, "dur": 75.977, + "args": { + "External id": 1441859,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 7234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854093248.254, "dur": 4.084, + "args": { + "External id": 1441860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854093248.961, "dur": 2.782, + "args": { + "External id": 1441861,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093250.569, "dur": 1.028, + "args": { + "External id": 1441862,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854093254.549, "dur": 10.024, + "args": { + "External id": 1441863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854093259.090, "dur": 5.018, + "args": { + "External id": 1441864,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093260.301, "dur": 3.690, + "args": { + "External id": 1441865,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854093265.356, "dur": 37.858, + "args": { + "External id": 1441866,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 7241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093317.168, "dur": 9.701, + "args": { + "External id": 1441867,"Record function id": 0, "Sequence number": 15348961, "Fwd thread id": 1, "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093318.114, "dur": 6.639, + "args": { + "External id": 1441868,"Sequence number": 15348961, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7243 + } + }, + { + "ph": "f", "id": 374, "pid": 2338706, "tid": 2379422, "ts": 6413854093318.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093320.392, "dur": 4.198, + "args": { + "External id": 1441869,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093321.202, "dur": 3.237, + "args": { + "External id": 1441870,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093330.776, "dur": 10.622, + "args": { + "External id": 1441871,"Record function id": 0, "Sequence number": 15348960, "Fwd thread id": 1, "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093331.770, "dur": 7.471, + "args": { + "External id": 1441872,"Sequence number": 15348960, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7247 + } + }, + { + "ph": "f", "id": 375, "pid": 2338706, "tid": 2379422, "ts": 6413854093331.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854093332.995, "dur": 6.056, + "args": { + "External id": 1441873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854093333.926, "dur": 4.631, + "args": { + "External id": 1441874,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093337.798, "dur": 0.661, + "args": { + "External id": 1441875,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854093345.845, "dur": 5.109, + "args": { + "External id": 1441876,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854093347.198, "dur": 3.205, + "args": { + "External id": 1441877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854093348.174, "dur": 1.871, + "args": { + "External id": 1441878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854093348.754, "dur": 1.194, + "args": { + "External id": 1441879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093354.381, "dur": 7.677, + "args": { + "External id": 1441880,"Record function id": 0, "Sequence number": 15348959, "Fwd thread id": 1, "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854093355.276, "dur": 3.796, + "args": { + "External id": 1441881,"Sequence number": 15348959, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7256 + } + }, + { + "ph": "f", "id": 376, "pid": 2338706, "tid": 2379422, "ts": 6413854093355.276, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093356.643, "dur": 2.273, + "args": { + "External id": 1441882,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093357.592, "dur": 1.183, + "args": { + "External id": 1441883,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854093367.295, "dur": 369.855, + "args": { + "External id": 1441884,"Record function id": 0, "Sequence number": 15348958, "Fwd thread id": 1, "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854093368.363, "dur": 344.621, + "args": { + "External id": 1441885,"Sequence number": 15348958, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7260 + } + }, + { + "ph": "f", "id": 377, "pid": 2338706, "tid": 2379422, "ts": 6413854093368.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854093389.392, "dur": 7.565, + "args": { + "External id": 1441886,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 7261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093392.548, "dur": 3.918, + "args": { + "External id": 1441887,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854093399.723, "dur": 4.291, + "args": { + "External id": 1441888,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 7263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093401.562, "dur": 2.210, + "args": { + "External id": 1441889,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854093405.692, "dur": 5.392, + "args": { + "External id": 1441890,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 7265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093407.512, "dur": 3.357, + "args": { + "External id": 1441891,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854093437.421, "dur": 249.049, + "args": { + "External id": 1441892,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854093524.541, "dur": 3.434, + "args": { + "External id": 1441893,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854093529.961, "dur": 2.187, + "args": { + "External id": 1441894,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854093533.234, "dur": 1.964, + "args": { + "External id": 1441895,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854093536.354, "dur": 2.527, + "args": { + "External id": 1441896,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093584.850, "dur": 2.820, + "args": { + "External id": 1441897,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093586.145, "dur": 1.253, + "args": { + "External id": 1441898,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854093589.572, "dur": 27.788, + "args": { + "External id": 1441899,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093595.049, "dur": 2.807, + "args": { + "External id": 1441900,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854093618.867, "dur": 4.241, + "args": { + "External id": 1441901,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854093622.251, "dur": 0.757, + "args": { + "External id": 1441902,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854093623.997, "dur": 18.800, + "args": { + "External id": 1441903,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093629.750, "dur": 0.462, + "args": { + "External id": 1441904,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854093699.841, "dur": 3.548, + "args": { + "External id": 1441905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854093706.580, "dur": 0.813, + "args": { + "External id": 1441906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2379422, + "ts": 6413854093709.399, "dur": 0.682, + "args": { + "External id": 1441907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854093745.170, "dur": 231.365, + "args": { + "External id": 1441908,"Record function id": 0, "Sequence number": 15348957, "Fwd thread id": 1, "Ev Idx": 7283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854093746.912, "dur": 222.305, + "args": { + "External id": 1441909,"Sequence number": 15348957, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7284 + } + }, + { + "ph": "f", "id": 378, "pid": 2338706, "tid": 2379422, "ts": 6413854093746.912, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854093767.266, "dur": 48.907, + "args": { + "External id": 1441910,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093770.966, "dur": 5.283, + "args": { + "External id": 1441911,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854093777.739, "dur": 37.808, + "args": { + "External id": 1441912,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], [8, 4096, 8, 128], []], "Ev Idx": 7287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854093826.509, "dur": 5.091, + "args": { + "External id": 1441913,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 7288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854093828.627, "dur": 2.666, + "args": { + "External id": 1441914,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854094008.342, "dur": 221.382, + "args": { + "External id": 1441915,"Record function id": 0, "Sequence number": 15348956, "Fwd thread id": 1, "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854094010.759, "dur": 210.073, + "args": { + "External id": 1441916,"Sequence number": 15348956, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7291 + } + }, + { + "ph": "f", "id": 379, "pid": 2338706, "tid": 2379422, "ts": 6413854094010.759, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2379422, + "ts": 6413854094025.213, "dur": 84.849, + "args": { + "External id": 1441917,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094028.398, "dur": 4.310, + "args": { + "External id": 1441918,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854094033.861, "dur": 75.029, + "args": { + "External id": 1441919,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], []], "Ev Idx": 7294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2379422, + "ts": 6413854094119.723, "dur": 6.659, + "args": { + "External id": 1441920,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 7295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094122.295, "dur": 3.728, + "args": { + "External id": 1441921,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094237.919, "dur": 17.722, + "args": { + "External id": 1441922,"Record function id": 0, "Sequence number": 15348955, "Fwd thread id": 1, "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094242.256, "dur": 10.008, + "args": { + "External id": 1441923,"Sequence number": 15348955, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7298 + } + }, + { + "ph": "f", "id": 380, "pid": 2338706, "tid": 2379422, "ts": 6413854094242.256, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094245.113, "dur": 6.933, + "args": { + "External id": 1441924,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094246.815, "dur": 5.063, + "args": { + "External id": 1441925,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094259.238, "dur": 8.161, + "args": { + "External id": 1441926,"Record function id": 0, "Sequence number": 15348954, "Fwd thread id": 1, "Ev Idx": 7301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094260.862, "dur": 4.235, + "args": { + "External id": 1441927,"Sequence number": 15348954, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 128]], "Ev Idx": 7302 + } + }, + { + "ph": "f", "id": 381, "pid": 2338706, "tid": 2379422, "ts": 6413854094260.862, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094262.525, "dur": 2.429, + "args": { + "External id": 1441928,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094263.572, "dur": 1.274, + "args": { + "External id": 1441929,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 128, 1], []], "Input Dims": [[8, 4096, 8, 128], []], "Ev Idx": 7304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094270.806, "dur": 7.509, + "args": { + "External id": 1441930,"Record function id": 0, "Sequence number": 15348953, "Fwd thread id": 1, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094271.864, "dur": 4.034, + "args": { + "External id": 1441931,"Sequence number": 15348953, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 7306 + } + }, + { + "ph": "f", "id": 382, "pid": 2338706, "tid": 2379422, "ts": 6413854094271.864, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094273.697, "dur": 2.064, + "args": { + "External id": 1441932,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094274.776, "dur": 0.894, + "args": { + "External id": 1441933,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094282.120, "dur": 10.688, + "args": { + "External id": 1441934,"Record function id": 0, "Sequence number": 15348952, "Fwd thread id": 1, "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094283.578, "dur": 5.407, + "args": { + "External id": 1441935,"Sequence number": 15348952, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 7310 + } + }, + { + "ph": "f", "id": 383, "pid": 2338706, "tid": 2379422, "ts": 6413854094283.578, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094284.958, "dur": 3.867, + "args": { + "External id": 1441936,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094287.697, "dur": 0.987, + "args": { + "External id": 1441937,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094296.205, "dur": 161.128, + "args": { + "External id": 1441938,"Record function id": 0, "Sequence number": 15348951, "Fwd thread id": 1, "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094297.235, "dur": 150.751, + "args": { + "External id": 1441939,"Sequence number": 15348951, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7314 + } + }, + { + "ph": "f", "id": 384, "pid": 2338706, "tid": 2379422, "ts": 6413854094297.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094301.946, "dur": 9.192, + "args": { + "External id": 1441940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094304.048, "dur": 6.491, + "args": { + "External id": 1441941,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 7316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094306.700, "dur": 3.543, + "args": { + "External id": 1441942,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 7317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854094315.235, "dur": 69.819, + "args": { + "External id": 1441943,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 7318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094386.493, "dur": 5.053, + "args": { + "External id": 1441944,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094387.424, "dur": 3.523, + "args": { + "External id": 1441945,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 7320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094389.178, "dur": 1.549, + "args": { + "External id": 1441946,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 7321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094394.031, "dur": 7.715, + "args": { + "External id": 1441947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094396.349, "dur": 4.681, + "args": { + "External id": 1441948,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094400.553, "dur": 0.396, + "args": { + "External id": 1441949,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854094402.455, "dur": 44.542, + "args": { + "External id": 1441950,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 7325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094462.797, "dur": 8.124, + "args": { + "External id": 1441951,"Record function id": 0, "Sequence number": 15348950, "Fwd thread id": 1, "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094463.757, "dur": 4.665, + "args": { + "External id": 1441952,"Sequence number": 15348950, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7327 + } + }, + { + "ph": "f", "id": 385, "pid": 2338706, "tid": 2379422, "ts": 6413854094463.757, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094465.484, "dur": 2.785, + "args": { + "External id": 1441953,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094466.707, "dur": 1.403, + "args": { + "External id": 1441954,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094474.155, "dur": 10.156, + "args": { + "External id": 1441955,"Record function id": 0, "Sequence number": 15348949, "Fwd thread id": 1, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094475.115, "dur": 6.898, + "args": { + "External id": 1441956,"Sequence number": 15348949, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7331 + } + }, + { + "ph": "f", "id": 386, "pid": 2338706, "tid": 2379422, "ts": 6413854094475.115, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094476.465, "dur": 5.335, + "args": { + "External id": 1441957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094479.321, "dur": 1.997, + "args": { + "External id": 1441958,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094480.780, "dur": 0.433, + "args": { + "External id": 1441959,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854094490.160, "dur": 12.634, + "args": { + "External id": 1441960,"Record function id": 0, "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854094491.900, "dur": 10.206, + "args": { + "External id": 1441961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854094494.695, "dur": 7.009, + "args": { + "External id": 1441962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854094495.826, "dur": 5.786, + "args": { + "External id": 1441963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094506.374, "dur": 7.413, + "args": { + "External id": 1441964,"Record function id": 0, "Sequence number": 15348948, "Fwd thread id": 1, "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094507.587, "dur": 3.936, + "args": { + "External id": 1441965,"Sequence number": 15348948, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4194304, 1024, 1]], "Input Dims": [[8, 4096, 1024]], "Ev Idx": 7340 + } + }, + { + "ph": "f", "id": 387, "pid": 2338706, "tid": 2379422, "ts": 6413854094507.587, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094509.307, "dur": 2.061, + "args": { + "External id": 1441966,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094510.251, "dur": 0.962, + "args": { + "External id": 1441967,"Record function id": 0, "Concrete Inputs": ["", "[32768, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 7342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094517.319, "dur": 92.164, + "args": { + "External id": 1441968,"Record function id": 0, "Sequence number": 15348947, "Fwd thread id": 1, "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094520.882, "dur": 80.901, + "args": { + "External id": 1441969,"Sequence number": 15348947, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7344 + } + }, + { + "ph": "f", "id": 388, "pid": 2338706, "tid": 2379422, "ts": 6413854094520.882, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094524.126, "dur": 3.348, + "args": { + "External id": 1441970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1024, 1]], "Input Dims": [[32768, 1024]], "Ev Idx": 7345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094524.713, "dur": 2.302, + "args": { + "External id": 1441971,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1024, 1], [], []], "Input Dims": [[32768, 1024], [], []], "Ev Idx": 7346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094526.220, "dur": 0.655, + "args": { + "External id": 1441972,"Record function id": 0, "Concrete Inputs": ["", "[1024, 32768]", "[1, 1024]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1024, 1], [], [], []], "Input Dims": [[32768, 1024], [], [], []], "Ev Idx": 7347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854094528.155, "dur": 25.832, + "args": { + "External id": 1441973,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096]], "Ev Idx": 7348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094555.036, "dur": 5.787, + "args": { + "External id": 1441974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094555.760, "dur": 4.590, + "args": { + "External id": 1441975,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 7350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094559.042, "dur": 1.145, + "args": { + "External id": 1441976,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 7351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094562.314, "dur": 4.383, + "args": { + "External id": 1441977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094563.602, "dur": 2.466, + "args": { + "External id": 1441978,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094565.271, "dur": 0.670, + "args": { + "External id": 1441979,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854094567.321, "dur": 33.770, + "args": { + "External id": 1441980,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096]], "Ev Idx": 7355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094614.808, "dur": 82.068, + "args": { + "External id": 1441981,"Record function id": 0, "Sequence number": 15348946, "Fwd thread id": 1, "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094659.190, "dur": 6.415, + "args": { + "External id": 1441982,"Sequence number": 15348946, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7357 + } + }, + { + "ph": "f", "id": 389, "pid": 2338706, "tid": 2379422, "ts": 6413854094659.190, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094662.908, "dur": 2.546, + "args": { + "External id": 1441983,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094663.964, "dur": 1.324, + "args": { + "External id": 1441984,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2379422, + "ts": 6413854094669.153, "dur": 25.060, + "args": { + "External id": 1441985,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094701.019, "dur": 10.821, + "args": { + "External id": 1441986,"Record function id": 0, "Sequence number": 15348945, "Fwd thread id": 1, "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094701.976, "dur": 6.846, + "args": { + "External id": 1441987,"Sequence number": 15348945, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7362 + } + }, + { + "ph": "f", "id": 390, "pid": 2338706, "tid": 2379422, "ts": 6413854094701.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094704.818, "dur": 3.822, + "args": { + "External id": 1441988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 1024]], "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094705.486, "dur": 2.632, + "args": { + "External id": 1441989,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 1024], [], []], "Ev Idx": 7364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094707.369, "dur": 0.590, + "args": { + "External id": 1441990,"Record function id": 0, "Concrete Inputs": ["", "[1024, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 1024], [], [], []], "Ev Idx": 7365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854094715.838, "dur": 6.480, + "args": { + "External id": 1441991,"Record function id": 0, "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854094717.424, "dur": 4.377, + "args": { + "External id": 1441992,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854094718.884, "dur": 2.431, + "args": { + "External id": 1441993,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854094719.741, "dur": 1.481, + "args": { + "External id": 1441994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094725.813, "dur": 7.470, + "args": { + "External id": 1441995,"Record function id": 0, "Sequence number": 15348944, "Fwd thread id": 1, "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094727.335, "dur": 3.166, + "args": { + "External id": 1441996,"Sequence number": 15348944, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7371 + } + }, + { + "ph": "f", "id": 391, "pid": 2338706, "tid": 2379422, "ts": 6413854094727.335, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094728.664, "dur": 1.676, + "args": { + "External id": 1441997,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094729.347, "dur": 0.847, + "args": { + "External id": 1441998,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094736.725, "dur": 106.408, + "args": { + "External id": 1441999,"Record function id": 0, "Sequence number": 15348943, "Fwd thread id": 1, "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094740.369, "dur": 91.867, + "args": { + "External id": 1442000,"Sequence number": 15348943, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7375 + } + }, + { + "ph": "f", "id": 392, "pid": 2338706, "tid": 2379422, "ts": 6413854094740.369, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094743.562, "dur": 2.661, + "args": { + "External id": 1442001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094743.969, "dur": 1.801, + "args": { + "External id": 1442002,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32768, 4096], [], []], "Ev Idx": 7377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094745.238, "dur": 0.436, + "args": { + "External id": 1442003,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32768]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854094746.969, "dur": 37.204, + "args": { + "External id": 1442004,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096]], "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094785.305, "dur": 5.969, + "args": { + "External id": 1442005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094785.828, "dur": 4.914, + "args": { + "External id": 1442006,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094790.103, "dur": 0.520, + "args": { + "External id": 1442007,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094792.873, "dur": 3.538, + "args": { + "External id": 1442008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094793.949, "dur": 1.878, + "args": { + "External id": 1442009,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094795.476, "dur": 0.278, + "args": { + "External id": 1442010,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854094797.150, "dur": 34.490, + "args": { + "External id": 1442011,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 7386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094847.603, "dur": 32.225, + "args": { + "External id": 1442012,"Record function id": 0, "Sequence number": 15348942, "Fwd thread id": 1, "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094848.516, "dur": 9.310, + "args": { + "External id": 1442013,"Sequence number": 15348942, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 7388 + } + }, + { + "ph": "f", "id": 393, "pid": 2338706, "tid": 2379422, "ts": 6413854094848.516, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094852.768, "dur": 4.911, + "args": { + "External id": 1442014,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094853.827, "dur": 3.689, + "args": { + "External id": 1442015,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854094860.465, "dur": 16.571, + "args": { + "External id": 1442016,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094883.503, "dur": 9.587, + "args": { + "External id": 1442017,"Record function id": 0, "Sequence number": 15348941, "Fwd thread id": 1, "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338706, "tid": 2379422, + "ts": 6413854094884.603, "dur": 5.466, + "args": { + "External id": 1442018,"Sequence number": 15348941, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7393 + } + }, + { + "ph": "f", "id": 394, "pid": 2338706, "tid": 2379422, "ts": 6413854094884.603, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2379422, + "ts": 6413854094885.769, "dur": 4.120, + "args": { + "External id": 1442019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 4096]], "Input Dims": [[4096, 4096]], "Ev Idx": 7394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2379422, + "ts": 6413854094886.575, "dur": 2.804, + "args": { + "External id": 1442020,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 4096], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 7395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854094888.680, "dur": 0.547, + "args": { + "External id": 1442021,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 4096], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 7396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854094896.969, "dur": 5.911, + "args": { + "External id": 1442022,"Record function id": 0, "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854094898.462, "dur": 3.896, + "args": { + "External id": 1442023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854094899.787, "dur": 1.969, + "args": { + "External id": 1442024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854094900.475, "dur": 1.192, + "args": { + "External id": 1442025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854094907.490, "dur": 459.603, + "args": { + "External id": 1442026,"Record function id": 0, "Sequence number": 15348940, "Fwd thread id": 1, "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854094909.245, "dur": 418.260, + "args": { + "External id": 1442027,"Sequence number": 15348940, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7402 + } + }, + { + "ph": "f", "id": 395, "pid": 2338706, "tid": 2379422, "ts": 6413854094909.245, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854094945.811, "dur": 2.128, + "args": { + "External id": 1442028,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854094946.704, "dur": 1.091, + "args": { + "External id": 1442029,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 7404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854094963.031, "dur": 3.667, + "args": { + "External id": 1442030,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854094976.051, "dur": 22.145, + "args": { + "External id": 1442031,"Record function id": 0, "Concrete Inputs": ["[132, 4096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854095191.852, "dur": 2.928, + "args": { + "External id": 1442032,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[132, 4096], []], "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854095212.612, "dur": 42.746, + "args": { + "External id": 1442033,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[540672, 4096, 1], [], [], []], "Input Dims": [[1, 132, 4096], [], [], []], "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095228.379, "dur": 0.980, + "args": { + "External id": 1442034,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 4096]", "[4096, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854095261.751, "dur": 38.523, + "args": { + "External id": 1442035,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], []], "Ev Idx": 7410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854095266.114, "dur": 33.948, + "args": { + "External id": 1442036,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[1, 4096], [], [], [], [], [], []], "Ev Idx": 7411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095274.530, "dur": 5.095, + "args": { + "External id": 1442037,"Record function id": 0, "Concrete Inputs": ["[1, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854095281.303, "dur": 18.151, + "args": { + "External id": 1442038,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1, 4096], [1, 4096], []], "Ev Idx": 7413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2379422, + "ts": 6413854095305.141, "dur": 2.579, + "args": { + "External id": 1442039,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1]], "Input Dims": [[1, 4096], [4096]], "Ev Idx": 7414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854095306.500, "dur": 1.073, + "args": { + "External id": 1442040,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[1, 4096], []], "Ev Idx": 7415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854095314.811, "dur": 4.999, + "args": { + "External id": 1442041,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854095318.561, "dur": 1.149, + "args": { + "External id": 1442042,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 7417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854095344.861, "dur": 17.044, + "args": { + "External id": 1442043,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 7418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854095380.814, "dur": 9.878, + "args": { + "External id": 1442044,"Record function id": 0, "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854095383.565, "dur": 6.463, + "args": { + "External id": 1442045,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854095386.252, "dur": 2.921, + "args": { + "External id": 1442046,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854095387.196, "dur": 1.845, + "args": { + "External id": 1442047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854095395.300, "dur": 3065.922, + "args": { + "External id": 1442048,"Record function id": 0, "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413854095428.690, "dur": 1091.015, + "args": { + "External id": 1442049,"Record function id": 0, "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 2338706, "tid": 2379422, + "ts": 6413854095453.628, "dur": 1056.762, + "args": { + "External id": 1442050,"Record function id": 0, "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413854095470.512, "dur": 1024.202, + "args": { + "External id": 1442051,"Record function id": 0, "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854095574.650, "dur": 5.735, + "args": { + "External id": 1442052,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854095598.443, "dur": 36.048, + "args": { + "External id": 1442053,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095605.320, "dur": 1.123, + "args": { + "External id": 1442054,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095608.654, "dur": 0.456, + "args": { + "External id": 1442055,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095610.137, "dur": 0.313, + "args": { + "External id": 1442056,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095614.545, "dur": 0.548, + "args": { + "External id": 1442057,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095616.007, "dur": 2.796, + "args": { + "External id": 1442058,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095620.172, "dur": 3.089, + "args": { + "External id": 1442059,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095624.469, "dur": 0.428, + "args": { + "External id": 1442060,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095626.405, "dur": 0.320, + "args": { + "External id": 1442061,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095629.682, "dur": 0.234, + "args": { + "External id": 1442062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854095648.108, "dur": 46.216, + "args": { + "External id": 1442063,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854095740.683, "dur": 133.711, + "args": { + "External id": 1442064,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854095753.804, "dur": 3.650, + "args": { + "External id": 1442065,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854095765.205, "dur": 11.706, + "args": { + "External id": 1442066,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854095769.948, "dur": 6.583, + "args": { + "External id": 1442067,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095773.911, "dur": 0.892, + "args": { + "External id": 1442068,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854095783.531, "dur": 29.081, + "args": { + "External id": 1442069,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095785.474, "dur": 0.273, + "args": { + "External id": 1442070,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095788.160, "dur": 2.458, + "args": { + "External id": 1442071,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095792.556, "dur": 0.366, + "args": { + "External id": 1442072,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095794.686, "dur": 0.267, + "args": { + "External id": 1442073,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095795.892, "dur": 0.293, + "args": { + "External id": 1442074,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095799.885, "dur": 0.463, + "args": { + "External id": 1442075,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095801.414, "dur": 0.724, + "args": { + "External id": 1442076,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095803.579, "dur": 2.366, + "args": { + "External id": 1442077,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854095807.179, "dur": 0.246, + "args": { + "External id": 1442078,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854095827.405, "dur": 36.932, + "args": { + "External id": 1442079,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854095942.661, "dur": 431.356, + "args": { + "External id": 1442080,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854095996.427, "dur": 371.236, + "args": { + "External id": 1442081,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7456, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854096010.011, "dur": 349.846, + "args": { + "External id": 1442082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854096402.880, "dur": 2.820, + "args": { + "External id": 1442083,"Record function id": 0, "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": 7458, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854096528.632, "dur": 1906.779, + "args": { + "External id": 1442084,"Sequence number": 15348939, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7459 + } + }, + { + "ph": "f", "id": 396, "pid": 2338706, "tid": 2379422, "ts": 6413854096528.632, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854096668.146, "dur": 110.668, + "args": { + "External id": 1442085,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854096826.409, "dur": 44.049, + "args": { + "External id": 1442086,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854096893.268, "dur": 50.020, + "args": { + "External id": 1442087,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854096953.434, "dur": 50.247, + "args": { + "External id": 1442088,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097013.392, "dur": 96.659, + "args": { + "External id": 1442089,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097125.668, "dur": 35.065, + "args": { + "External id": 1442090,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097172.617, "dur": 30.404, + "args": { + "External id": 1442091,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854097235.827, "dur": 30.458, + "args": { + "External id": 1442092,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854097291.334, "dur": 35.653, + "args": { + "External id": 1442093,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854097357.019, "dur": 18.702, + "args": { + "External id": 1442094,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854097393.548, "dur": 15.871, + "args": { + "External id": 1442095,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097419.039, "dur": 36.268, + "args": { + "External id": 1442096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097458.717, "dur": 33.343, + "args": { + "External id": 1442097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854097524.277, "dur": 256.826, + "args": { + "External id": 1442098,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854097612.014, "dur": 8.216, + "args": { + "External id": 1442099,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854097622.299, "dur": 2.583, + "args": { + "External id": 1442100,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854097625.977, "dur": 2.420, + "args": { + "External id": 1442101,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854097629.688, "dur": 6.024, + "args": { + "External id": 1442102,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854097679.845, "dur": 8.058, + "args": { + "External id": 1442103,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854097684.662, "dur": 3.089, + "args": { + "External id": 1442104,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854097689.743, "dur": 31.619, + "args": { + "External id": 1442105,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854097695.848, "dur": 1.837, + "args": { + "External id": 1442106,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854097722.717, "dur": 2.049, + "args": { + "External id": 1442107,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854097723.847, "dur": 0.830, + "args": { + "External id": 1442108,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854097725.412, "dur": 13.070, + "args": { + "External id": 1442109,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854097727.279, "dur": 0.541, + "args": { + "External id": 1442110,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854097821.985, "dur": 30.098, + "args": { + "External id": 1442111,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854097873.798, "dur": 17.435, + "args": { + "External id": 1442112,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097899.231, "dur": 37.934, + "args": { + "External id": 1442113,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854097943.350, "dur": 54.729, + "args": { + "External id": 1442114,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854098012.893, "dur": 24.869, + "args": { + "External id": 1442115,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854098043.398, "dur": 67.446, + "args": { + "External id": 1442116,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854098121.884, "dur": 30.454, + "args": { + "External id": 1442117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854098159.186, "dur": 29.161, + "args": { + "External id": 1442118,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854098215.135, "dur": 28.028, + "args": { + "External id": 1442119,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854098263.970, "dur": 29.818, + "args": { + "External id": 1442120,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854098312.447, "dur": 17.787, + "args": { + "External id": 1442121,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854098350.428, "dur": 14.580, + "args": { + "External id": 1442122,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854098382.367, "dur": 18.871, + "args": { + "External id": 1442123,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 7498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098484.291, "dur": 16.559, + "args": { + "External id": 1442124,"Record function id": 0, "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098488.815, "dur": 11.025, + "args": { + "External id": 1442125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098493.388, "dur": 5.597, + "args": { + "External id": 1442126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098494.961, "dur": 3.938, + "args": { + "External id": 1442127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098504.737, "dur": 5.330, + "args": { + "External id": 1442128,"Record function id": 0, "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098506.251, "dur": 3.283, + "args": { + "External id": 1442129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098507.176, "dur": 1.895, + "args": { + "External id": 1442130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098508.042, "dur": 0.943, + "args": { + "External id": 1442131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098513.451, "dur": 7.553, + "args": { + "External id": 1442132,"Record function id": 0, "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098515.460, "dur": 5.083, + "args": { + "External id": 1442133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098516.033, "dur": 4.082, + "args": { + "External id": 1442134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098516.721, "dur": 3.310, + "args": { + "External id": 1442135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098524.374, "dur": 4.495, + "args": { + "External id": 1442136,"Record function id": 0, "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098525.716, "dur": 2.662, + "args": { + "External id": 1442137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098526.522, "dur": 1.251, + "args": { + "External id": 1442138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098526.967, "dur": 0.729, + "args": { + "External id": 1442139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098532.026, "dur": 4.243, + "args": { + "External id": 1442140,"Record function id": 0, "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098533.554, "dur": 2.281, + "args": { + "External id": 1442141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098534.183, "dur": 1.033, + "args": { + "External id": 1442142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098534.510, "dur": 0.640, + "args": { + "External id": 1442143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098539.475, "dur": 4.825, + "args": { + "External id": 1442144,"Record function id": 0, "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098540.794, "dur": 3.070, + "args": { + "External id": 1442145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098541.728, "dur": 1.729, + "args": { + "External id": 1442146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098542.366, "dur": 1.027, + "args": { + "External id": 1442147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098547.542, "dur": 4.621, + "args": { + "External id": 1442148,"Record function id": 0, "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098549.174, "dur": 2.574, + "args": { + "External id": 1442149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098549.912, "dur": 1.440, + "args": { + "External id": 1442150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098550.596, "dur": 0.692, + "args": { + "External id": 1442151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098555.248, "dur": 6.521, + "args": { + "External id": 1442152,"Record function id": 0, "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098556.586, "dur": 4.770, + "args": { + "External id": 1442153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098557.312, "dur": 3.457, + "args": { + "External id": 1442154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098559.889, "dur": 0.814, + "args": { + "External id": 1442155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098564.898, "dur": 4.333, + "args": { + "External id": 1442156,"Record function id": 0, "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854098566.403, "dur": 2.406, + "args": { + "External id": 1442157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098566.849, "dur": 1.324, + "args": { + "External id": 1442158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854098567.484, "dur": 0.624, + "args": { + "External id": 1442159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854098573.442, "dur": 284657.557, + "args": { + "External id": 1442160,"Record function id": 0, "Sequence number": 15348938, "Fwd thread id": 1, "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854098574.972, "dur": 284645.881, + "args": { + "External id": 1442161,"Sequence number": 15348938, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7536 + } + }, + { + "ph": "f", "id": 397, "pid": 2338706, "tid": 2379422, "ts": 6413854098574.972, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413854098610.156, "dur": 45.855, + "args": { + "External id": 1442162,"Record function id": 0, "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413854098665.010, "dur": 100.142, + "args": { + "External id": 1442163,"Record function id": 0, "Ev Idx": 7538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 2338706, "tid": 2379422, + "ts": 6413854098771.158, "dur": 284441.479, + "args": { + "External id": 1442164,"Record function id": 0, "Ev Idx": 7539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854098831.189, "dur": 7.710, + "args": { + "External id": 1442165,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854098852.467, "dur": 6.972, + "args": { + "External id": 1442166,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854098876.682, "dur": 283357.703, + "args": { + "External id": 1442167,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854098894.967, "dur": 283324.389, + "args": { + "External id": 1442168,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854099174.508, "dur": 7.788, + "args": { + "External id": 1442169,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854099223.659, "dur": 282944.273, + "args": { + "External id": 1442170,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 7545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854099226.924, "dur": 282939.629, + "args": { + "External id": 1442171,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 7546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854099231.041, "dur": 13.615, + "args": { + "External id": 1442172,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854099246.811, "dur": 282914.143, + "args": { + "External id": 1442173,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 7548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854382358.713, "dur": 14.564, + "args": { + "External id": 1442174,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 7549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854382362.792, "dur": 10.059, + "args": { + "External id": 1442175,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854382415.750, "dur": 312.872, + "args": { + "External id": 1442176,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 7551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854382450.632, "dur": 273.244, + "args": { + "External id": 1442177,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7552, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854382464.791, "dur": 253.605, + "args": { + "External id": 1442178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 7553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854382752.913, "dur": 2.045, + "args": { + "External id": 1442179,"Record function id": 0, "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": 7554, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854382812.568, "dur": 7.374, + "args": { + "External id": 1442180,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854382834.055, "dur": 38.857, + "args": { + "External id": 1442181,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854382885.537, "dur": 1.670, + "args": { + "External id": 1442182,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854382893.335, "dur": 13.460, + "args": { + "External id": 1442183,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854382913.147, "dur": 1.043, + "args": { + "External id": 1442184,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854382919.500, "dur": 13.097, + "args": { + "External id": 1442185,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854382938.207, "dur": 1.064, + "args": { + "External id": 1442186,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854382945.206, "dur": 12.467, + "args": { + "External id": 1442187,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854382962.220, "dur": 3.156, + "args": { + "External id": 1442188,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854382970.559, "dur": 33.304, + "args": { + "External id": 1442189,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383011.796, "dur": 1.729, + "args": { + "External id": 1442190,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854383021.414, "dur": 13.719, + "args": { + "External id": 1442191,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383040.349, "dur": 0.890, + "args": { + "External id": 1442192,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854383045.887, "dur": 46.659, + "args": { + "External id": 1442193,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383101.388, "dur": 1.630, + "args": { + "External id": 1442194,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854383109.156, "dur": 13.290, + "args": { + "External id": 1442195,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383129.669, "dur": 0.961, + "args": { + "External id": 1442196,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854383135.387, "dur": 13.456, + "args": { + "External id": 1442197,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 7572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854383247.945, "dur": 3085.272, + "args": { + "External id": 1442198,"Record function id": 0, "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413854383270.044, "dur": 1161.360, + "args": { + "External id": 1442199,"Record function id": 0, "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413854383285.238, "dur": 374.481, + "args": { + "External id": 1442200,"Record function id": 0, "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383388.267, "dur": 4.810, + "args": { + "External id": 1442201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383396.916, "dur": 0.865, + "args": { + "External id": 1442202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383399.538, "dur": 0.842, + "args": { + "External id": 1442203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383402.525, "dur": 3.568, + "args": { + "External id": 1442204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383407.511, "dur": 0.842, + "args": { + "External id": 1442205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383410.277, "dur": 0.979, + "args": { + "External id": 1442206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383414.847, "dur": 0.939, + "args": { + "External id": 1442207,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383435.685, "dur": 1.296, + "args": { + "External id": 1442208,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383438.966, "dur": 1.174, + "args": { + "External id": 1442209,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854383441.655, "dur": 0.860, + "args": { + "External id": 1442210,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854383466.373, "dur": 162.968, + "args": { + "External id": 1442211,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854383485.889, "dur": 138.858, + "args": { + "External id": 1442212,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854383507.394, "dur": 14.977, + "args": { + "External id": 1442213,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854383528.356, "dur": 68.592, + "args": { + "External id": 1442214,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 7589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854383531.234, "dur": 65.346, + "args": { + "External id": 1442215,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 7590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383534.411, "dur": 8.850, + "args": { + "External id": 1442216,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854383544.881, "dur": 50.890, + "args": { + "External id": 1442217,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 7592 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.23", "pid": 2338706, "tid": 2379422, + "ts": 6413854383758.552, "dur": 665.316, + "args": { + "External id": 1442218,"Record function id": 0, "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413854383776.775, "dur": 633.070, + "args": { + "External id": 1442219,"Record function id": 0, "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854383841.052, "dur": 4.910, + "args": { + "External id": 1442220,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854383863.444, "dur": 30.593, + "args": { + "External id": 1442221,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383868.150, "dur": 1.369, + "args": { + "External id": 1442222,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383871.667, "dur": 2.103, + "args": { + "External id": 1442223,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383875.143, "dur": 0.664, + "args": { + "External id": 1442224,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383877.262, "dur": 0.505, + "args": { + "External id": 1442225,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383880.660, "dur": 0.256, + "args": { + "External id": 1442226,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383882.392, "dur": 0.543, + "args": { + "External id": 1442227,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383884.332, "dur": 2.519, + "args": { + "External id": 1442228,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383888.787, "dur": 0.364, + "args": { + "External id": 1442229,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854383890.374, "dur": 0.286, + "args": { + "External id": 1442230,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854383904.729, "dur": 43.422, + "args": { + "External id": 1442231,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854383998.089, "dur": 162.142, + "args": { + "External id": 1442232,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854384009.917, "dur": 4.811, + "args": { + "External id": 1442233,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854384021.171, "dur": 11.583, + "args": { + "External id": 1442234,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854384025.689, "dur": 6.640, + "args": { + "External id": 1442235,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384029.606, "dur": 0.939, + "args": { + "External id": 1442236,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854384040.438, "dur": 61.555, + "args": { + "External id": 1442237,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384042.667, "dur": 0.511, + "args": { + "External id": 1442238,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384045.986, "dur": 0.328, + "args": { + "External id": 1442239,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384047.614, "dur": 0.533, + "args": { + "External id": 1442240,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384049.751, "dur": 35.710, + "args": { + "External id": 1442241,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384088.330, "dur": 0.425, + "args": { + "External id": 1442242,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384090.178, "dur": 0.538, + "args": { + "External id": 1442243,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384093.543, "dur": 0.335, + "args": { + "External id": 1442244,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384095.609, "dur": 0.299, + "args": { + "External id": 1442245,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854384097.505, "dur": 0.281, + "args": { + "External id": 1442246,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854384117.454, "dur": 34.512, + "args": { + "External id": 1442247,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854384211.053, "dur": 125.017, + "args": { + "External id": 1442248,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854384242.532, "dur": 90.125, + "args": { + "External id": 1442249,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7624, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854384252.263, "dur": 75.933, + "args": { + "External id": 1442250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854384354.107, "dur": 1.745, + "args": { + "External id": 1442251,"Record function id": 0, "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": 7626, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854384439.081, "dur": 1865.869, + "args": { + "External id": 1442252,"Sequence number": 15348937, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7627 + } + }, + { + "ph": "f", "id": 398, "pid": 2338706, "tid": 2379422, "ts": 6413854384439.081, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854384557.646, "dur": 103.756, + "args": { + "External id": 1442253,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854384706.678, "dur": 41.703, + "args": { + "External id": 1442254,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854384765.984, "dur": 49.810, + "args": { + "External id": 1442255,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854384826.444, "dur": 31.875, + "args": { + "External id": 1442256,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854384867.481, "dur": 32.336, + "args": { + "External id": 1442257,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854384908.071, "dur": 27.495, + "args": { + "External id": 1442258,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854384943.025, "dur": 29.792, + "args": { + "External id": 1442259,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854385022.959, "dur": 63.353, + "args": { + "External id": 1442260,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854385115.433, "dur": 36.003, + "args": { + "External id": 1442261,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854385175.920, "dur": 19.562, + "args": { + "External id": 1442262,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854385212.443, "dur": 19.564, + "args": { + "External id": 1442263,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385240.230, "dur": 43.206, + "args": { + "External id": 1442264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385286.901, "dur": 32.142, + "args": { + "External id": 1442265,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854385353.330, "dur": 258.063, + "args": { + "External id": 1442266,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854385435.911, "dur": 6.504, + "args": { + "External id": 1442267,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854385444.406, "dur": 2.967, + "args": { + "External id": 1442268,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854385448.317, "dur": 2.487, + "args": { + "External id": 1442269,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854385451.713, "dur": 3.938, + "args": { + "External id": 1442270,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854385499.739, "dur": 5.128, + "args": { + "External id": 1442271,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854385501.807, "dur": 2.882, + "args": { + "External id": 1442272,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854385506.762, "dur": 34.426, + "args": { + "External id": 1442273,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854385512.919, "dur": 2.825, + "args": { + "External id": 1442274,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854385542.968, "dur": 2.168, + "args": { + "External id": 1442275,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854385544.508, "dur": 0.527, + "args": { + "External id": 1442276,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854385545.878, "dur": 17.650, + "args": { + "External id": 1442277,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854385548.300, "dur": 3.060, + "args": { + "External id": 1442278,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854385650.054, "dur": 28.025, + "args": { + "External id": 1442279,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854385697.473, "dur": 16.346, + "args": { + "External id": 1442280,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385721.390, "dur": 36.824, + "args": { + "External id": 1442281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385764.587, "dur": 37.770, + "args": { + "External id": 1442282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385812.584, "dur": 19.925, + "args": { + "External id": 1442283,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385838.084, "dur": 46.972, + "args": { + "External id": 1442284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385900.910, "dur": 31.789, + "args": { + "External id": 1442285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854385939.487, "dur": 30.525, + "args": { + "External id": 1442286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854386015.149, "dur": 31.863, + "args": { + "External id": 1442287,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854386107.606, "dur": 29.571, + "args": { + "External id": 1442288,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854386153.911, "dur": 20.777, + "args": { + "External id": 1442289,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854386194.511, "dur": 14.432, + "args": { + "External id": 1442290,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854386254.189, "dur": 18.732, + "args": { + "External id": 1442291,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 7666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386355.921, "dur": 17.705, + "args": { + "External id": 1442292,"Record function id": 0, "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386359.627, "dur": 13.072, + "args": { + "External id": 1442293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386364.083, "dur": 7.564, + "args": { + "External id": 1442294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386365.892, "dur": 5.660, + "args": { + "External id": 1442295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386377.512, "dur": 5.228, + "args": { + "External id": 1442296,"Record function id": 0, "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386379.004, "dur": 3.245, + "args": { + "External id": 1442297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386380.252, "dur": 1.521, + "args": { + "External id": 1442298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386380.674, "dur": 1.012, + "args": { + "External id": 1442299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386386.221, "dur": 7.276, + "args": { + "External id": 1442300,"Record function id": 0, "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386387.617, "dur": 5.453, + "args": { + "External id": 1442301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386388.192, "dur": 4.182, + "args": { + "External id": 1442302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386389.113, "dur": 3.181, + "args": { + "External id": 1442303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386396.599, "dur": 68.914, + "args": { + "External id": 1442304,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386461.753, "dur": 3.104, + "args": { + "External id": 1442305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386462.763, "dur": 1.484, + "args": { + "External id": 1442306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386463.179, "dur": 0.950, + "args": { + "External id": 1442307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386468.982, "dur": 12.139, + "args": { + "External id": 1442308,"Record function id": 0, "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386478.304, "dur": 2.410, + "args": { + "External id": 1442309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386478.869, "dur": 0.984, + "args": { + "External id": 1442310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386479.193, "dur": 0.593, + "args": { + "External id": 1442311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386484.367, "dur": 6.029, + "args": { + "External id": 1442312,"Record function id": 0, "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386485.566, "dur": 4.408, + "args": { + "External id": 1442313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386486.030, "dur": 3.224, + "args": { + "External id": 1442314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386488.537, "dur": 0.616, + "args": { + "External id": 1442315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386493.634, "dur": 3.934, + "args": { + "External id": 1442316,"Record function id": 0, "Ev Idx": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386494.823, "dur": 2.318, + "args": { + "External id": 1442317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386495.508, "dur": 1.078, + "args": { + "External id": 1442318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386495.856, "dur": 0.647, + "args": { + "External id": 1442319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386501.267, "dur": 4.152, + "args": { + "External id": 1442320,"Record function id": 0, "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386502.580, "dur": 2.321, + "args": { + "External id": 1442321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386503.037, "dur": 1.241, + "args": { + "External id": 1442322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386503.435, "dur": 0.780, + "args": { + "External id": 1442323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386509.120, "dur": 3.743, + "args": { + "External id": 1442324,"Record function id": 0, "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854386510.243, "dur": 2.221, + "args": { + "External id": 1442325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386510.798, "dur": 1.070, + "args": { + "External id": 1442326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854386511.197, "dur": 0.604, + "args": { + "External id": 1442327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854386517.394, "dur": 77963.222, + "args": { + "External id": 1442328,"Record function id": 0, "Sequence number": 15348936, "Fwd thread id": 1, "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854386519.048, "dur": 77951.677, + "args": { + "External id": 1442329,"Sequence number": 15348936, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7704 + } + }, + { + "ph": "f", "id": 399, "pid": 2338706, "tid": 2379422, "ts": 6413854386519.048, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413854386552.714, "dur": 42.596, + "args": { + "External id": 1442330,"Record function id": 0, "Ev Idx": 7705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413854386603.375, "dur": 70.060, + "args": { + "External id": 1442331,"Record function id": 0, "Ev Idx": 7706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 2338706, "tid": 2379422, + "ts": 6413854386679.988, "dur": 77782.143, + "args": { + "External id": 1442332,"Record function id": 0, "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854386772.518, "dur": 7.260, + "args": { + "External id": 1442333,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854386788.785, "dur": 6.484, + "args": { + "External id": 1442334,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854386811.482, "dur": 76626.143, + "args": { + "External id": 1442335,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854386826.375, "dur": 76597.587, + "args": { + "External id": 1442336,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854387035.707, "dur": 56.400, + "args": { + "External id": 1442337,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854387124.461, "dur": 76252.201, + "args": { + "External id": 1442338,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 7713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854387128.018, "dur": 76247.268, + "args": { + "External id": 1442339,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 7714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854387134.889, "dur": 9.697, + "args": { + "External id": 1442340,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854387146.688, "dur": 76223.524, + "args": { + "External id": 1442341,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 7716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854463551.504, "dur": 11.992, + "args": { + "External id": 1442342,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 7717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854463555.273, "dur": 7.828, + "args": { + "External id": 1442343,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854463597.422, "dur": 408.278, + "args": { + "External id": 1442344,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854463631.141, "dur": 368.543, + "args": { + "External id": 1442345,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7720, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854463646.838, "dur": 324.910, + "args": { + "External id": 1442346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 7721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854464030.505, "dur": 2.650, + "args": { + "External id": 1442347,"Record function id": 0, "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": 7722, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464128.540, "dur": 7.423, + "args": { + "External id": 1442348,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464149.045, "dur": 39.092, + "args": { + "External id": 1442349,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464198.371, "dur": 1.525, + "args": { + "External id": 1442350,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464205.965, "dur": 12.531, + "args": { + "External id": 1442351,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464224.437, "dur": 1.149, + "args": { + "External id": 1442352,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464232.040, "dur": 11.332, + "args": { + "External id": 1442353,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464248.272, "dur": 0.928, + "args": { + "External id": 1442354,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464254.186, "dur": 10.412, + "args": { + "External id": 1442355,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464269.404, "dur": 3.508, + "args": { + "External id": 1442356,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464276.729, "dur": 11.178, + "args": { + "External id": 1442357,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464292.249, "dur": 1.510, + "args": { + "External id": 1442358,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464298.559, "dur": 10.924, + "args": { + "External id": 1442359,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464316.631, "dur": 0.995, + "args": { + "External id": 1442360,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464341.780, "dur": 12.687, + "args": { + "External id": 1442361,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464360.870, "dur": 1.044, + "args": { + "External id": 1442362,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464367.297, "dur": 10.390, + "args": { + "External id": 1442363,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464382.586, "dur": 0.830, + "args": { + "External id": 1442364,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464389.952, "dur": 10.115, + "args": { + "External id": 1442365,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 7740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854464497.224, "dur": 3019.239, + "args": { + "External id": 1442366,"Record function id": 0, "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413854464519.063, "dur": 1110.638, + "args": { + "External id": 1442367,"Record function id": 0, "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413854464536.363, "dur": 323.961, + "args": { + "External id": 1442368,"Record function id": 0, "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464627.440, "dur": 4.173, + "args": { + "External id": 1442369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464634.917, "dur": 0.733, + "args": { + "External id": 1442370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464637.796, "dur": 0.916, + "args": { + "External id": 1442371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464640.418, "dur": 3.093, + "args": { + "External id": 1442372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464645.660, "dur": 1.127, + "args": { + "External id": 1442373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464648.248, "dur": 0.927, + "args": { + "External id": 1442374,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464650.938, "dur": 0.867, + "args": { + "External id": 1442375,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464656.141, "dur": 0.962, + "args": { + "External id": 1442376,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464658.994, "dur": 0.807, + "args": { + "External id": 1442377,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854464661.147, "dur": 0.789, + "args": { + "External id": 1442378,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854464679.881, "dur": 151.929, + "args": { + "External id": 1442379,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854464697.765, "dur": 129.702, + "args": { + "External id": 1442380,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854464714.738, "dur": 14.447, + "args": { + "External id": 1442381,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854464736.964, "dur": 64.515, + "args": { + "External id": 1442382,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 7757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854464739.721, "dur": 61.453, + "args": { + "External id": 1442383,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854464745.220, "dur": 7.530, + "args": { + "External id": 1442384,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854464754.619, "dur": 45.912, + "args": { + "External id": 1442385,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 7760 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.22", "pid": 2338706, "tid": 2379422, + "ts": 6413854464952.019, "dur": 669.826, + "args": { + "External id": 1442386,"Record function id": 0, "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413854464969.456, "dur": 638.795, + "args": { + "External id": 1442387,"Record function id": 0, "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854465089.147, "dur": 7.362, + "args": { + "External id": 1442388,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854465116.077, "dur": 34.594, + "args": { + "External id": 1442389,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465121.426, "dur": 1.882, + "args": { + "External id": 1442390,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465125.779, "dur": 2.168, + "args": { + "External id": 1442391,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465129.257, "dur": 0.527, + "args": { + "External id": 1442392,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465131.637, "dur": 0.559, + "args": { + "External id": 1442393,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465134.943, "dur": 0.395, + "args": { + "External id": 1442394,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465136.520, "dur": 0.384, + "args": { + "External id": 1442395,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465138.318, "dur": 3.361, + "args": { + "External id": 1442396,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465144.784, "dur": 0.388, + "args": { + "External id": 1442397,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465146.539, "dur": 0.458, + "args": { + "External id": 1442398,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854465162.854, "dur": 48.191, + "args": { + "External id": 1442399,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854465244.773, "dur": 118.013, + "args": { + "External id": 1442400,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854465256.024, "dur": 3.944, + "args": { + "External id": 1442401,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854465265.815, "dur": 10.411, + "args": { + "External id": 1442402,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854465270.313, "dur": 5.489, + "args": { + "External id": 1442403,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465273.704, "dur": 0.578, + "args": { + "External id": 1442404,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854465283.029, "dur": 28.166, + "args": { + "External id": 1442405,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465284.950, "dur": 0.418, + "args": { + "External id": 1442406,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465288.135, "dur": 0.639, + "args": { + "External id": 1442407,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465290.262, "dur": 0.391, + "args": { + "External id": 1442408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465292.157, "dur": 4.098, + "args": { + "External id": 1442409,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465297.759, "dur": 0.385, + "args": { + "External id": 1442410,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465299.320, "dur": 0.322, + "args": { + "External id": 1442411,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465303.155, "dur": 0.401, + "args": { + "External id": 1442412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465305.109, "dur": 0.348, + "args": { + "External id": 1442413,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854465307.315, "dur": 0.325, + "args": { + "External id": 1442414,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854465325.025, "dur": 30.274, + "args": { + "External id": 1442415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854465410.127, "dur": 124.059, + "args": { + "External id": 1442416,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854465441.122, "dur": 89.562, + "args": { + "External id": 1442417,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7792, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854465453.043, "dur": 72.743, + "args": { + "External id": 1442418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854465554.086, "dur": 1.940, + "args": { + "External id": 1442419,"Record function id": 0, "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": 7794, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854465637.452, "dur": 1849.929, + "args": { + "External id": 1442420,"Sequence number": 15348935, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7795 + } + }, + { + "ph": "f", "id": 400, "pid": 2338706, "tid": 2379422, "ts": 6413854465637.452, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854465750.615, "dur": 103.547, + "args": { + "External id": 1442421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854465899.134, "dur": 42.097, + "args": { + "External id": 1442422,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854465959.201, "dur": 72.714, + "args": { + "External id": 1442423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466046.095, "dur": 73.039, + "args": { + "External id": 1442424,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466131.657, "dur": 34.941, + "args": { + "External id": 1442425,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466173.251, "dur": 27.645, + "args": { + "External id": 1442426,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466208.817, "dur": 28.883, + "args": { + "External id": 1442427,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854466266.485, "dur": 26.999, + "args": { + "External id": 1442428,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854466316.711, "dur": 28.622, + "args": { + "External id": 1442429,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854466369.787, "dur": 20.724, + "args": { + "External id": 1442430,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854466407.050, "dur": 15.142, + "args": { + "External id": 1442431,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466430.272, "dur": 35.349, + "args": { + "External id": 1442432,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466468.996, "dur": 32.633, + "args": { + "External id": 1442433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854466534.474, "dur": 249.108, + "args": { + "External id": 1442434,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854466612.563, "dur": 6.657, + "args": { + "External id": 1442435,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854466621.268, "dur": 3.060, + "args": { + "External id": 1442436,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854466625.337, "dur": 2.399, + "args": { + "External id": 1442437,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854466628.871, "dur": 3.168, + "args": { + "External id": 1442438,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854466676.034, "dur": 5.261, + "args": { + "External id": 1442439,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854466678.327, "dur": 2.827, + "args": { + "External id": 1442440,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854466685.435, "dur": 32.775, + "args": { + "External id": 1442441,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854466692.180, "dur": 1.641, + "args": { + "External id": 1442442,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854466719.913, "dur": 1.599, + "args": { + "External id": 1442443,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854466720.917, "dur": 0.507, + "args": { + "External id": 1442444,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854466722.326, "dur": 18.495, + "args": { + "External id": 1442445,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854466724.683, "dur": 2.943, + "args": { + "External id": 1442446,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854466824.044, "dur": 33.318, + "args": { + "External id": 1442447,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854466877.331, "dur": 18.061, + "args": { + "External id": 1442448,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466902.753, "dur": 41.737, + "args": { + "External id": 1442449,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854466950.876, "dur": 82.353, + "args": { + "External id": 1442450,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854467093.566, "dur": 33.091, + "args": { + "External id": 1442451,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854467134.440, "dur": 35.477, + "args": { + "External id": 1442452,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854467177.818, "dur": 28.977, + "args": { + "External id": 1442453,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854467214.347, "dur": 31.184, + "args": { + "External id": 1442454,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854467274.739, "dur": 28.889, + "args": { + "External id": 1442455,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854467322.853, "dur": 27.257, + "args": { + "External id": 1442456,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854467369.408, "dur": 19.136, + "args": { + "External id": 1442457,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854467406.002, "dur": 15.461, + "args": { + "External id": 1442458,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854467438.888, "dur": 17.973, + "args": { + "External id": 1442459,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 7834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467539.637, "dur": 17.067, + "args": { + "External id": 1442460,"Record function id": 0, "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467543.038, "dur": 12.721, + "args": { + "External id": 1442461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467547.253, "dur": 7.542, + "args": { + "External id": 1442462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467550.459, "dur": 4.208, + "args": { + "External id": 1442463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467560.889, "dur": 5.199, + "args": { + "External id": 1442464,"Record function id": 0, "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467562.495, "dur": 3.011, + "args": { + "External id": 1442465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467563.227, "dur": 1.577, + "args": { + "External id": 1442466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467563.787, "dur": 0.918, + "args": { + "External id": 1442467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467569.452, "dur": 6.699, + "args": { + "External id": 1442468,"Record function id": 0, "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467571.029, "dur": 4.700, + "args": { + "External id": 1442469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467571.570, "dur": 3.612, + "args": { + "External id": 1442470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467572.409, "dur": 2.662, + "args": { + "External id": 1442471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 7846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467579.595, "dur": 4.182, + "args": { + "External id": 1442472,"Record function id": 0, "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467580.609, "dur": 2.742, + "args": { + "External id": 1442473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467581.342, "dur": 1.298, + "args": { + "External id": 1442474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467581.732, "dur": 0.840, + "args": { + "External id": 1442475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 7850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467587.049, "dur": 4.448, + "args": { + "External id": 1442476,"Record function id": 0, "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467588.437, "dur": 2.623, + "args": { + "External id": 1442477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467589.154, "dur": 1.306, + "args": { + "External id": 1442478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467589.690, "dur": 0.705, + "args": { + "External id": 1442479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467594.704, "dur": 4.007, + "args": { + "External id": 1442480,"Record function id": 0, "Ev Idx": 7855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467595.829, "dur": 2.471, + "args": { + "External id": 1442481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467596.490, "dur": 1.359, + "args": { + "External id": 1442482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467596.942, "dur": 0.839, + "args": { + "External id": 1442483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467601.887, "dur": 4.266, + "args": { + "External id": 1442484,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467603.282, "dur": 2.434, + "args": { + "External id": 1442485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467603.891, "dur": 1.369, + "args": { + "External id": 1442486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467604.644, "dur": 0.553, + "args": { + "External id": 1442487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467609.277, "dur": 6.310, + "args": { + "External id": 1442488,"Record function id": 0, "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467610.449, "dur": 4.742, + "args": { + "External id": 1442489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467611.111, "dur": 3.408, + "args": { + "External id": 1442490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467613.728, "dur": 0.716, + "args": { + "External id": 1442491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 7866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467618.644, "dur": 3.598, + "args": { + "External id": 1442492,"Record function id": 0, "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854467619.688, "dur": 2.122, + "args": { + "External id": 1442493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467620.164, "dur": 1.073, + "args": { + "External id": 1442494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854467620.491, "dur": 0.672, + "args": { + "External id": 1442495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 7870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854467626.416, "dur": 74635.291, + "args": { + "External id": 1442496,"Record function id": 0, "Sequence number": 15348934, "Fwd thread id": 1, "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854467627.856, "dur": 74623.608, + "args": { + "External id": 1442497,"Sequence number": 15348934, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7872 + } + }, + { + "ph": "f", "id": 401, "pid": 2338706, "tid": 2379422, "ts": 6413854467627.856, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413854467657.913, "dur": 40.781, + "args": { + "External id": 1442498,"Record function id": 0, "Ev Idx": 7873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413854467706.980, "dur": 69.733, + "args": { + "External id": 1442499,"Record function id": 0, "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 2338706, "tid": 2379422, + "ts": 6413854467782.603, "dur": 74459.852, + "args": { + "External id": 1442500,"Record function id": 0, "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854467874.306, "dur": 6.875, + "args": { + "External id": 1442501,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854467890.945, "dur": 6.751, + "args": { + "External id": 1442502,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854467912.065, "dur": 73295.316, + "args": { + "External id": 1442503,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854467926.612, "dur": 73267.425, + "args": { + "External id": 1442504,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 7879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854468115.186, "dur": 21.094, + "args": { + "External id": 1442505,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854468163.143, "dur": 72978.682, + "args": { + "External id": 1442506,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854468166.412, "dur": 72974.171, + "args": { + "External id": 1442507,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854468173.389, "dur": 11.132, + "args": { + "External id": 1442508,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854468186.776, "dur": 72948.835, + "args": { + "External id": 1442509,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 7884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854541318.821, "dur": 12.802, + "args": { + "External id": 1442510,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 7885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854541322.564, "dur": 8.724, + "args": { + "External id": 1442511,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854541364.233, "dur": 417.683, + "args": { + "External id": 1442512,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 7887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854541397.561, "dur": 379.380, + "args": { + "External id": 1442513,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7888, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854541410.841, "dur": 360.815, + "args": { + "External id": 1442514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 7889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854541803.686, "dur": 2.134, + "args": { + "External id": 1442515,"Record function id": 0, "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": 7890, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854541864.237, "dur": 6.853, + "args": { + "External id": 1442516,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854541883.837, "dur": 33.541, + "args": { + "External id": 1442517,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854541927.518, "dur": 1.685, + "args": { + "External id": 1442518,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854541935.621, "dur": 11.034, + "args": { + "External id": 1442519,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854541952.986, "dur": 1.123, + "args": { + "External id": 1442520,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854541974.482, "dur": 33.429, + "args": { + "External id": 1442521,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542018.646, "dur": 1.784, + "args": { + "External id": 1442522,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542025.933, "dur": 10.906, + "args": { + "External id": 1442523,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 7898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542041.790, "dur": 3.808, + "args": { + "External id": 1442524,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542049.640, "dur": 41.593, + "args": { + "External id": 1442525,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 7900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542099.327, "dur": 2.628, + "args": { + "External id": 1442526,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542107.231, "dur": 11.375, + "args": { + "External id": 1442527,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 7902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542125.771, "dur": 0.791, + "args": { + "External id": 1442528,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542130.293, "dur": 10.400, + "args": { + "External id": 1442529,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542144.666, "dur": 1.019, + "args": { + "External id": 1442530,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542150.125, "dur": 9.519, + "args": { + "External id": 1442531,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 7906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542163.620, "dur": 1.018, + "args": { + "External id": 1442532,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542169.267, "dur": 10.605, + "args": { + "External id": 1442533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 7908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854542278.374, "dur": 3006.433, + "args": { + "External id": 1442534,"Record function id": 0, "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413854542301.462, "dur": 1086.635, + "args": { + "External id": 1442535,"Record function id": 0, "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413854542316.794, "dur": 321.561, + "args": { + "External id": 1442536,"Record function id": 0, "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542405.642, "dur": 4.153, + "args": { + "External id": 1442537,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 7912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542413.242, "dur": 0.996, + "args": { + "External id": 1442538,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542416.162, "dur": 0.709, + "args": { + "External id": 1442539,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542418.733, "dur": 2.807, + "args": { + "External id": 1442540,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542425.844, "dur": 0.918, + "args": { + "External id": 1442541,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542428.449, "dur": 0.827, + "args": { + "External id": 1442542,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 7917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542430.874, "dur": 0.969, + "args": { + "External id": 1442543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 7918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542433.377, "dur": 0.989, + "args": { + "External id": 1442544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542437.625, "dur": 0.793, + "args": { + "External id": 1442545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854542440.154, "dur": 1.021, + "args": { + "External id": 1442546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 7921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854542459.207, "dur": 150.627, + "args": { + "External id": 1442547,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854542476.004, "dur": 129.588, + "args": { + "External id": 1442548,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 7923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854542492.619, "dur": 16.155, + "args": { + "External id": 1442549,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854542513.246, "dur": 65.320, + "args": { + "External id": 1442550,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 7925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854542518.145, "dur": 59.999, + "args": { + "External id": 1442551,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 7926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542522.114, "dur": 7.964, + "args": { + "External id": 1442552,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542531.608, "dur": 45.795, + "args": { + "External id": 1442553,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 7928 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.21", "pid": 2338706, "tid": 2379422, + "ts": 6413854542730.882, "dur": 649.315, + "args": { + "External id": 1442554,"Record function id": 0, "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413854542747.875, "dur": 619.275, + "args": { + "External id": 1442555,"Record function id": 0, "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854542807.703, "dur": 5.009, + "args": { + "External id": 1442556,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854542828.814, "dur": 30.342, + "args": { + "External id": 1442557,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542833.856, "dur": 2.499, + "args": { + "External id": 1442558,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542838.309, "dur": 0.522, + "args": { + "External id": 1442559,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542840.216, "dur": 0.656, + "args": { + "External id": 1442560,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542843.039, "dur": 0.543, + "args": { + "External id": 1442561,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542845.086, "dur": 0.472, + "args": { + "External id": 1442562,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542846.681, "dur": 0.343, + "args": { + "External id": 1442563,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542849.494, "dur": 2.754, + "args": { + "External id": 1442564,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542853.605, "dur": 0.574, + "args": { + "External id": 1442565,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542855.417, "dur": 0.805, + "args": { + "External id": 1442566,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854542873.746, "dur": 41.264, + "args": { + "External id": 1442567,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854542944.907, "dur": 173.939, + "args": { + "External id": 1442568,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 7943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854542954.563, "dur": 3.936, + "args": { + "External id": 1442569,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854542963.996, "dur": 9.908, + "args": { + "External id": 1442570,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854542968.176, "dur": 5.271, + "args": { + "External id": 1442571,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 7946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854542971.389, "dur": 0.685, + "args": { + "External id": 1442572,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 7947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854543001.030, "dur": 27.121, + "args": { + "External id": 1442573,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 7948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543003.527, "dur": 0.700, + "args": { + "External id": 1442574,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543005.676, "dur": 2.147, + "args": { + "External id": 1442575,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543009.098, "dur": 0.504, + "args": { + "External id": 1442576,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543010.832, "dur": 2.649, + "args": { + "External id": 1442577,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543016.076, "dur": 0.379, + "args": { + "External id": 1442578,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543017.601, "dur": 0.244, + "args": { + "External id": 1442579,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543019.217, "dur": 0.615, + "args": { + "External id": 1442580,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543022.387, "dur": 0.481, + "args": { + "External id": 1442581,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854543024.162, "dur": 0.424, + "args": { + "External id": 1442582,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 7957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854543040.507, "dur": 68.437, + "args": { + "External id": 1442583,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 7958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854543168.922, "dur": 124.328, + "args": { + "External id": 1442584,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854543202.336, "dur": 87.278, + "args": { + "External id": 1442585,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7960, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854543212.441, "dur": 72.916, + "args": { + "External id": 1442586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854543311.594, "dur": 1.762, + "args": { + "External id": 1442587,"Record function id": 0, "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": 7962, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854543435.341, "dur": 1823.352, + "args": { + "External id": 1442588,"Sequence number": 15348933, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 7963 + } + }, + { + "ph": "f", "id": 402, "pid": 2338706, "tid": 2379422, "ts": 6413854543435.341, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854543554.325, "dur": 106.128, + "args": { + "External id": 1442589,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 7964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854543709.649, "dur": 41.496, + "args": { + "External id": 1442590,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 7965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854543768.141, "dur": 48.460, + "args": { + "External id": 1442591,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 7966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854543826.889, "dur": 30.645, + "args": { + "External id": 1442592,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854543865.625, "dur": 31.982, + "args": { + "External id": 1442593,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854543903.545, "dur": 26.998, + "args": { + "External id": 1442594,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 7969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854543936.995, "dur": 27.865, + "args": { + "External id": 1442595,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 7970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854544013.033, "dur": 26.549, + "args": { + "External id": 1442596,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 7971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854544099.617, "dur": 33.694, + "args": { + "External id": 1442597,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854544157.076, "dur": 20.142, + "args": { + "External id": 1442598,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 7973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854544194.071, "dur": 16.191, + "args": { + "External id": 1442599,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 7974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544218.863, "dur": 42.769, + "args": { + "External id": 1442600,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544265.532, "dur": 32.513, + "args": { + "External id": 1442601,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854544330.270, "dur": 252.235, + "args": { + "External id": 1442602,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 7977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854544415.097, "dur": 6.362, + "args": { + "External id": 1442603,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854544423.538, "dur": 2.609, + "args": { + "External id": 1442604,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854544427.439, "dur": 3.131, + "args": { + "External id": 1442605,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854544431.840, "dur": 3.674, + "args": { + "External id": 1442606,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854544480.131, "dur": 5.283, + "args": { + "External id": 1442607,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854544482.348, "dur": 2.894, + "args": { + "External id": 1442608,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854544487.174, "dur": 31.188, + "args": { + "External id": 1442609,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854544492.940, "dur": 1.810, + "args": { + "External id": 1442610,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854544520.349, "dur": 1.770, + "args": { + "External id": 1442611,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854544521.221, "dur": 0.815, + "args": { + "External id": 1442612,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 7987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854544525.474, "dur": 16.055, + "args": { + "External id": 1442613,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 7988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854544527.452, "dur": 2.913, + "args": { + "External id": 1442614,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854544624.908, "dur": 27.807, + "args": { + "External id": 1442615,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854544672.508, "dur": 15.985, + "args": { + "External id": 1442616,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544695.825, "dur": 40.031, + "args": { + "External id": 1442617,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544742.843, "dur": 42.744, + "args": { + "External id": 1442618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544794.650, "dur": 21.224, + "args": { + "External id": 1442619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 7994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544821.717, "dur": 47.086, + "args": { + "External id": 1442620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544885.339, "dur": 33.023, + "args": { + "External id": 1442621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 7996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854544925.641, "dur": 29.713, + "args": { + "External id": 1442622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 7997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854545003.358, "dur": 31.182, + "args": { + "External id": 1442623,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 7998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854545090.465, "dur": 30.828, + "args": { + "External id": 1442624,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854545142.646, "dur": 17.716, + "args": { + "External id": 1442625,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854545181.117, "dur": 14.540, + "args": { + "External id": 1442626,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854545209.887, "dur": 15.980, + "args": { + "External id": 1442627,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545307.608, "dur": 18.047, + "args": { + "External id": 1442628,"Record function id": 0, "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545312.474, "dur": 12.160, + "args": { + "External id": 1442629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545317.360, "dur": 6.388, + "args": { + "External id": 1442630,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545319.266, "dur": 4.405, + "args": { + "External id": 1442631,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545329.893, "dur": 5.476, + "args": { + "External id": 1442632,"Record function id": 0, "Ev Idx": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545331.508, "dur": 3.342, + "args": { + "External id": 1442633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545332.512, "dur": 1.753, + "args": { + "External id": 1442634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545333.218, "dur": 0.977, + "args": { + "External id": 1442635,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545338.578, "dur": 7.622, + "args": { + "External id": 1442636,"Record function id": 0, "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545340.091, "dur": 5.608, + "args": { + "External id": 1442637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545340.761, "dur": 4.342, + "args": { + "External id": 1442638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545341.570, "dur": 3.471, + "args": { + "External id": 1442639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545349.391, "dur": 4.688, + "args": { + "External id": 1442640,"Record function id": 0, "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545350.760, "dur": 2.893, + "args": { + "External id": 1442641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545351.875, "dur": 1.367, + "args": { + "External id": 1442642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545352.278, "dur": 0.891, + "args": { + "External id": 1442643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545357.079, "dur": 4.219, + "args": { + "External id": 1442644,"Record function id": 0, "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545358.379, "dur": 2.505, + "args": { + "External id": 1442645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545359.319, "dur": 1.095, + "args": { + "External id": 1442646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545359.580, "dur": 0.757, + "args": { + "External id": 1442647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545364.428, "dur": 6.203, + "args": { + "External id": 1442648,"Record function id": 0, "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545365.584, "dur": 4.579, + "args": { + "External id": 1442649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545366.116, "dur": 3.600, + "args": { + "External id": 1442650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545368.906, "dur": 0.711, + "args": { + "External id": 1442651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545373.960, "dur": 4.634, + "args": { + "External id": 1442652,"Record function id": 0, "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545375.725, "dur": 2.433, + "args": { + "External id": 1442653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545376.506, "dur": 1.241, + "args": { + "External id": 1442654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545376.966, "dur": 0.706, + "args": { + "External id": 1442655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545381.688, "dur": 4.439, + "args": { + "External id": 1442656,"Record function id": 0, "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545382.962, "dur": 2.751, + "args": { + "External id": 1442657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545383.766, "dur": 1.342, + "args": { + "External id": 1442658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545384.204, "dur": 0.830, + "args": { + "External id": 1442659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545389.153, "dur": 4.403, + "args": { + "External id": 1442660,"Record function id": 0, "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854545390.871, "dur": 2.286, + "args": { + "External id": 1442661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545391.520, "dur": 1.235, + "args": { + "External id": 1442662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854545391.874, "dur": 0.807, + "args": { + "External id": 1442663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854545398.188, "dur": 69326.898, + "args": { + "External id": 1442664,"Record function id": 0, "Sequence number": 15348932, "Fwd thread id": 1, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854545399.603, "dur": 69314.332, + "args": { + "External id": 1442665,"Sequence number": 15348932, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8040 + } + }, + { + "ph": "f", "id": 403, "pid": 2338706, "tid": 2379422, "ts": 6413854545399.603, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413854545431.154, "dur": 41.265, + "args": { + "External id": 1442666,"Record function id": 0, "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413854545479.849, "dur": 68.574, + "args": { + "External id": 1442667,"Record function id": 0, "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 2338706, "tid": 2379422, + "ts": 6413854545554.627, "dur": 69151.751, + "args": { + "External id": 1442668,"Record function id": 0, "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854545646.514, "dur": 6.613, + "args": { + "External id": 1442669,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854545663.252, "dur": 6.414, + "args": { + "External id": 1442670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854545686.599, "dur": 68040.086, + "args": { + "External id": 1442671,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854545700.440, "dur": 68012.498, + "args": { + "External id": 1442672,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854545821.807, "dur": 18.635, + "args": { + "External id": 1442673,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854545861.206, "dur": 67809.386, + "args": { + "External id": 1442674,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854545865.675, "dur": 67803.853, + "args": { + "External id": 1442675,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854545869.825, "dur": 8.370, + "args": { + "External id": 1442676,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854545897.514, "dur": 67766.774, + "args": { + "External id": 1442677,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854613842.358, "dur": 12.800, + "args": { + "External id": 1442678,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854613846.087, "dur": 8.740, + "args": { + "External id": 1442679,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854613893.018, "dur": 424.160, + "args": { + "External id": 1442680,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854613925.932, "dur": 385.276, + "args": { + "External id": 1442681,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8056, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854613937.902, "dur": 367.152, + "args": { + "External id": 1442682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854614343.768, "dur": 2.301, + "args": { + "External id": 1442683,"Record function id": 0, "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": 8058, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614410.355, "dur": 6.875, + "args": { + "External id": 1442684,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614430.242, "dur": 34.568, + "args": { + "External id": 1442685,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614475.466, "dur": 1.723, + "args": { + "External id": 1442686,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614482.911, "dur": 12.022, + "args": { + "External id": 1442687,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614500.709, "dur": 1.186, + "args": { + "External id": 1442688,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614507.008, "dur": 11.122, + "args": { + "External id": 1442689,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614523.534, "dur": 1.121, + "args": { + "External id": 1442690,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614529.910, "dur": 10.789, + "args": { + "External id": 1442691,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614545.571, "dur": 3.041, + "args": { + "External id": 1442692,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614552.283, "dur": 10.921, + "args": { + "External id": 1442693,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614567.935, "dur": 1.684, + "args": { + "External id": 1442694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614576.069, "dur": 10.198, + "args": { + "External id": 1442695,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614590.985, "dur": 0.765, + "args": { + "External id": 1442696,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614595.771, "dur": 10.898, + "args": { + "External id": 1442697,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614611.051, "dur": 0.894, + "args": { + "External id": 1442698,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614615.921, "dur": 9.727, + "args": { + "External id": 1442699,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854614632.455, "dur": 0.785, + "args": { + "External id": 1442700,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854614637.934, "dur": 10.721, + "args": { + "External id": 1442701,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854614740.328, "dur": 2976.990, + "args": { + "External id": 1442702,"Record function id": 0, "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413854614761.467, "dur": 1121.222, + "args": { + "External id": 1442703,"Record function id": 0, "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413854614777.826, "dur": 395.367, + "args": { + "External id": 1442704,"Record function id": 0, "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614866.624, "dur": 4.273, + "args": { + "External id": 1442705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614874.328, "dur": 1.108, + "args": { + "External id": 1442706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614877.094, "dur": 1.106, + "args": { + "External id": 1442707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614880.544, "dur": 3.078, + "args": { + "External id": 1442708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614885.355, "dur": 1.210, + "args": { + "External id": 1442709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614888.178, "dur": 0.913, + "args": { + "External id": 1442710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614890.779, "dur": 1.058, + "args": { + "External id": 1442711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614895.200, "dur": 1.298, + "args": { + "External id": 1442712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614898.027, "dur": 0.755, + "args": { + "External id": 1442713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854614900.820, "dur": 1.094, + "args": { + "External id": 1442714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854614919.028, "dur": 215.715, + "args": { + "External id": 1442715,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854614936.004, "dur": 192.980, + "args": { + "External id": 1442716,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854614955.538, "dur": 16.954, + "args": { + "External id": 1442717,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854614976.565, "dur": 124.733, + "args": { + "External id": 1442718,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854614997.522, "dur": 103.307, + "args": { + "External id": 1442719,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615001.854, "dur": 8.682, + "args": { + "External id": 1442720,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854615012.507, "dur": 87.044, + "args": { + "External id": 1442721,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.20", "pid": 2338706, "tid": 2379422, + "ts": 6413854615275.434, "dur": 599.691, + "args": { + "External id": 1442722,"Record function id": 0, "Ev Idx": 8097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413854615295.397, "dur": 565.989, + "args": { + "External id": 1442723,"Record function id": 0, "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854615363.341, "dur": 6.279, + "args": { + "External id": 1442724,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854615386.918, "dur": 32.499, + "args": { + "External id": 1442725,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615392.463, "dur": 1.932, + "args": { + "External id": 1442726,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615396.453, "dur": 1.697, + "args": { + "External id": 1442727,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615399.548, "dur": 0.773, + "args": { + "External id": 1442728,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615401.612, "dur": 0.533, + "args": { + "External id": 1442729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615405.109, "dur": 0.270, + "args": { + "External id": 1442730,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615406.462, "dur": 0.390, + "args": { + "External id": 1442731,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615408.249, "dur": 3.123, + "args": { + "External id": 1442732,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615413.959, "dur": 0.474, + "args": { + "External id": 1442733,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615415.459, "dur": 0.566, + "args": { + "External id": 1442734,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854615431.448, "dur": 43.805, + "args": { + "External id": 1442735,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854615506.335, "dur": 114.325, + "args": { + "External id": 1442736,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854615516.591, "dur": 3.629, + "args": { + "External id": 1442737,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854615525.589, "dur": 10.684, + "args": { + "External id": 1442738,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854615530.283, "dur": 5.560, + "args": { + "External id": 1442739,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615534.008, "dur": 0.552, + "args": { + "External id": 1442740,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854615542.529, "dur": 26.770, + "args": { + "External id": 1442741,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615544.380, "dur": 0.566, + "args": { + "External id": 1442742,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615547.893, "dur": 0.632, + "args": { + "External id": 1442743,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615549.559, "dur": 0.540, + "args": { + "External id": 1442744,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615551.218, "dur": 4.281, + "args": { + "External id": 1442745,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615556.967, "dur": 0.405, + "args": { + "External id": 1442746,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615558.739, "dur": 0.335, + "args": { + "External id": 1442747,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615561.807, "dur": 0.396, + "args": { + "External id": 1442748,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615563.599, "dur": 0.537, + "args": { + "External id": 1442749,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854615565.240, "dur": 0.431, + "args": { + "External id": 1442750,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854615582.094, "dur": 31.123, + "args": { + "External id": 1442751,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854615666.294, "dur": 121.388, + "args": { + "External id": 1442752,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854615696.808, "dur": 87.466, + "args": { + "External id": 1442753,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8128, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854615708.579, "dur": 71.102, + "args": { + "External id": 1442754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854615807.535, "dur": 1.760, + "args": { + "External id": 1442755,"Record function id": 0, "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": 8130, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854615890.078, "dur": 1802.096, + "args": { + "External id": 1442756,"Sequence number": 15348931, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8131 + } + }, + { + "ph": "f", "id": 404, "pid": 2338706, "tid": 2379422, "ts": 6413854615890.078, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616024.124, "dur": 144.387, + "args": { + "External id": 1442757,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854616224.894, "dur": 40.343, + "args": { + "External id": 1442758,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616284.775, "dur": 49.525, + "args": { + "External id": 1442759,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616344.141, "dur": 31.025, + "args": { + "External id": 1442760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616383.467, "dur": 32.888, + "args": { + "External id": 1442761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616422.902, "dur": 27.258, + "args": { + "External id": 1442762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616456.510, "dur": 28.869, + "args": { + "External id": 1442763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854616511.947, "dur": 21.630, + "args": { + "External id": 1442764,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854616555.684, "dur": 27.565, + "args": { + "External id": 1442765,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854616607.049, "dur": 17.960, + "args": { + "External id": 1442766,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854616638.989, "dur": 14.608, + "args": { + "External id": 1442767,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616661.149, "dur": 36.567, + "args": { + "External id": 1442768,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854616701.366, "dur": 32.164, + "args": { + "External id": 1442769,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854616765.731, "dur": 264.942, + "args": { + "External id": 1442770,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854616844.762, "dur": 6.336, + "args": { + "External id": 1442771,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854616852.978, "dur": 2.885, + "args": { + "External id": 1442772,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854616857.543, "dur": 2.467, + "args": { + "External id": 1442773,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854616861.018, "dur": 4.118, + "args": { + "External id": 1442774,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854616908.237, "dur": 5.227, + "args": { + "External id": 1442775,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854616910.314, "dur": 2.981, + "args": { + "External id": 1442776,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854616917.640, "dur": 29.699, + "args": { + "External id": 1442777,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854616923.104, "dur": 1.748, + "args": { + "External id": 1442778,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854616948.621, "dur": 1.827, + "args": { + "External id": 1442779,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854616949.651, "dur": 0.699, + "args": { + "External id": 1442780,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854616951.777, "dur": 16.877, + "args": { + "External id": 1442781,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854616953.856, "dur": 2.835, + "args": { + "External id": 1442782,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854617105.873, "dur": 32.497, + "args": { + "External id": 1442783,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854617161.924, "dur": 17.798, + "args": { + "External id": 1442784,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854617188.636, "dur": 49.121, + "args": { + "External id": 1442785,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854617244.442, "dur": 39.142, + "args": { + "External id": 1442786,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854617293.409, "dur": 40.519, + "args": { + "External id": 1442787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854617348.069, "dur": 34.312, + "args": { + "External id": 1442788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854617390.101, "dur": 26.627, + "args": { + "External id": 1442789,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854617423.218, "dur": 32.774, + "args": { + "External id": 1442790,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854617480.453, "dur": 28.274, + "args": { + "External id": 1442791,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854617526.343, "dur": 29.799, + "args": { + "External id": 1442792,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854617574.611, "dur": 18.761, + "args": { + "External id": 1442793,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854617612.291, "dur": 15.610, + "args": { + "External id": 1442794,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854617643.245, "dur": 16.968, + "args": { + "External id": 1442795,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617740.279, "dur": 18.127, + "args": { + "External id": 1442796,"Record function id": 0, "Ev Idx": 8171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617745.775, "dur": 11.533, + "args": { + "External id": 1442797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617750.610, "dur": 5.616, + "args": { + "External id": 1442798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617752.161, "dur": 3.971, + "args": { + "External id": 1442799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617762.510, "dur": 4.916, + "args": { + "External id": 1442800,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617764.127, "dur": 2.797, + "args": { + "External id": 1442801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617764.993, "dur": 1.407, + "args": { + "External id": 1442802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617765.463, "dur": 0.827, + "args": { + "External id": 1442803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617770.735, "dur": 7.357, + "args": { + "External id": 1442804,"Record function id": 0, "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617772.307, "dur": 5.305, + "args": { + "External id": 1442805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617773.070, "dur": 3.923, + "args": { + "External id": 1442806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617773.727, "dur": 3.169, + "args": { + "External id": 1442807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617781.371, "dur": 4.411, + "args": { + "External id": 1442808,"Record function id": 0, "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617782.783, "dur": 2.569, + "args": { + "External id": 1442809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617783.570, "dur": 1.331, + "args": { + "External id": 1442810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617784.064, "dur": 0.762, + "args": { + "External id": 1442811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617788.980, "dur": 4.752, + "args": { + "External id": 1442812,"Record function id": 0, "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617790.169, "dur": 3.151, + "args": { + "External id": 1442813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617791.102, "dur": 1.428, + "args": { + "External id": 1442814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617791.758, "dur": 0.709, + "args": { + "External id": 1442815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617796.903, "dur": 77.085, + "args": { + "External id": 1442816,"Record function id": 0, "Ev Idx": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617867.410, "dur": 5.964, + "args": { + "External id": 1442817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617868.527, "dur": 4.113, + "args": { + "External id": 1442818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617871.546, "dur": 0.957, + "args": { + "External id": 1442819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617883.628, "dur": 4.208, + "args": { + "External id": 1442820,"Record function id": 0, "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617884.927, "dur": 2.507, + "args": { + "External id": 1442821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617885.671, "dur": 1.052, + "args": { + "External id": 1442822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617885.987, "dur": 0.654, + "args": { + "External id": 1442823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617891.818, "dur": 4.605, + "args": { + "External id": 1442824,"Record function id": 0, "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617893.565, "dur": 2.407, + "args": { + "External id": 1442825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617894.031, "dur": 1.199, + "args": { + "External id": 1442826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617894.425, "dur": 0.738, + "args": { + "External id": 1442827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617900.146, "dur": 3.956, + "args": { + "External id": 1442828,"Record function id": 0, "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854617901.495, "dur": 2.184, + "args": { + "External id": 1442829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617902.005, "dur": 1.219, + "args": { + "External id": 1442830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854617902.491, "dur": 0.669, + "args": { + "External id": 1442831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854617908.532, "dur": 67799.790, + "args": { + "External id": 1442832,"Record function id": 0, "Sequence number": 15348930, "Fwd thread id": 1, "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854617910.030, "dur": 67788.508, + "args": { + "External id": 1442833,"Sequence number": 15348930, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8208 + } + }, + { + "ph": "f", "id": 405, "pid": 2338706, "tid": 2379422, "ts": 6413854617910.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413854617940.668, "dur": 56.302, + "args": { + "External id": 1442834,"Record function id": 0, "Ev Idx": 8209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413854618007.621, "dur": 108.798, + "args": { + "External id": 1442835,"Record function id": 0, "Ev Idx": 8210 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 2338706, "tid": 2379422, + "ts": 6413854618124.167, "dur": 67566.784, + "args": { + "External id": 1442836,"Record function id": 0, "Ev Idx": 8211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854618220.877, "dur": 8.155, + "args": { + "External id": 1442837,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854618239.784, "dur": 7.147, + "args": { + "External id": 1442838,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854618266.310, "dur": 66443.590, + "args": { + "External id": 1442839,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854618290.831, "dur": 66405.605, + "args": { + "External id": 1442840,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854618434.396, "dur": 18.791, + "args": { + "External id": 1442841,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854618473.584, "dur": 66171.943, + "args": { + "External id": 1442842,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854618476.687, "dur": 66167.784, + "args": { + "External id": 1442843,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854618482.764, "dur": 9.417, + "args": { + "External id": 1442844,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854618494.489, "dur": 66144.883, + "args": { + "External id": 1442845,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854684823.259, "dur": 12.369, + "args": { + "External id": 1442846,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854684826.730, "dur": 8.538, + "args": { + "External id": 1442847,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854684866.833, "dur": 429.594, + "args": { + "External id": 1442848,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854684900.997, "dur": 389.503, + "args": { + "External id": 1442849,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8224, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854684916.532, "dur": 368.003, + "args": { + "External id": 1442850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854685324.650, "dur": 2.351, + "args": { + "External id": 1442851,"Record function id": 0, "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": 8226, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685393.987, "dur": 6.873, + "args": { + "External id": 1442852,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685414.037, "dur": 34.457, + "args": { + "External id": 1442853,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685459.029, "dur": 1.793, + "args": { + "External id": 1442854,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685467.761, "dur": 11.595, + "args": { + "External id": 1442855,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685485.113, "dur": 1.316, + "args": { + "External id": 1442856,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685493.743, "dur": 11.302, + "args": { + "External id": 1442857,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685509.935, "dur": 1.109, + "args": { + "External id": 1442858,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685515.048, "dur": 10.730, + "args": { + "External id": 1442859,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685530.901, "dur": 3.468, + "args": { + "External id": 1442860,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685539.123, "dur": 10.945, + "args": { + "External id": 1442861,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685554.396, "dur": 1.493, + "args": { + "External id": 1442862,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685559.753, "dur": 10.119, + "args": { + "External id": 1442863,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685576.581, "dur": 0.853, + "args": { + "External id": 1442864,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685581.993, "dur": 10.126, + "args": { + "External id": 1442865,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685596.975, "dur": 0.880, + "args": { + "External id": 1442866,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685601.851, "dur": 10.093, + "args": { + "External id": 1442867,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685616.446, "dur": 0.870, + "args": { + "External id": 1442868,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685623.802, "dur": 10.088, + "args": { + "External id": 1442869,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854685722.950, "dur": 2967.671, + "args": { + "External id": 1442870,"Record function id": 0, "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413854685742.974, "dur": 1122.944, + "args": { + "External id": 1442871,"Record function id": 0, "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413854685757.607, "dur": 388.132, + "args": { + "External id": 1442872,"Record function id": 0, "Ev Idx": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685845.335, "dur": 4.094, + "args": { + "External id": 1442873,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685852.735, "dur": 0.851, + "args": { + "External id": 1442874,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685855.639, "dur": 0.887, + "args": { + "External id": 1442875,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685858.286, "dur": 3.120, + "args": { + "External id": 1442876,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685863.313, "dur": 0.890, + "args": { + "External id": 1442877,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685865.786, "dur": 1.034, + "args": { + "External id": 1442878,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685868.626, "dur": 0.641, + "args": { + "External id": 1442879,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685873.068, "dur": 1.191, + "args": { + "External id": 1442880,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685875.906, "dur": 0.938, + "args": { + "External id": 1442881,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854685878.281, "dur": 0.794, + "args": { + "External id": 1442882,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854685897.108, "dur": 213.518, + "args": { + "External id": 1442883,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854685915.100, "dur": 189.252, + "args": { + "External id": 1442884,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854685933.465, "dur": 14.193, + "args": { + "External id": 1442885,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854685953.869, "dur": 85.404, + "args": { + "External id": 1442886,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854685956.647, "dur": 82.194, + "args": { + "External id": 1442887,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854685960.259, "dur": 7.820, + "args": { + "External id": 1442888,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854685969.581, "dur": 68.280, + "args": { + "External id": 1442889,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8264 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 2338706, "tid": 2379422, + "ts": 6413854686246.805, "dur": 611.103, + "args": { + "External id": 1442890,"Record function id": 0, "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413854686264.410, "dur": 580.489, + "args": { + "External id": 1442891,"Record function id": 0, "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854686329.787, "dur": 6.043, + "args": { + "External id": 1442892,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854686353.341, "dur": 32.588, + "args": { + "External id": 1442893,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686358.817, "dur": 1.610, + "args": { + "External id": 1442894,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686362.143, "dur": 1.767, + "args": { + "External id": 1442895,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686366.018, "dur": 0.596, + "args": { + "External id": 1442896,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686367.581, "dur": 0.606, + "args": { + "External id": 1442897,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686371.121, "dur": 0.453, + "args": { + "External id": 1442898,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686372.736, "dur": 0.385, + "args": { + "External id": 1442899,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686374.843, "dur": 2.708, + "args": { + "External id": 1442900,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686380.135, "dur": 0.404, + "args": { + "External id": 1442901,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686382.071, "dur": 0.626, + "args": { + "External id": 1442902,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854686397.905, "dur": 44.327, + "args": { + "External id": 1442903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854686472.211, "dur": 135.130, + "args": { + "External id": 1442904,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854686482.413, "dur": 3.192, + "args": { + "External id": 1442905,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854686491.238, "dur": 10.340, + "args": { + "External id": 1442906,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854686495.812, "dur": 5.357, + "args": { + "External id": 1442907,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686499.089, "dur": 0.776, + "args": { + "External id": 1442908,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854686529.102, "dur": 27.477, + "args": { + "External id": 1442909,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686531.085, "dur": 0.587, + "args": { + "External id": 1442910,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686534.439, "dur": 0.424, + "args": { + "External id": 1442911,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686535.879, "dur": 0.275, + "args": { + "External id": 1442912,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686537.926, "dur": 3.601, + "args": { + "External id": 1442913,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686543.056, "dur": 0.463, + "args": { + "External id": 1442914,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686545.545, "dur": 0.352, + "args": { + "External id": 1442915,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686549.312, "dur": 0.267, + "args": { + "External id": 1442916,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686550.977, "dur": 0.367, + "args": { + "External id": 1442917,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854686552.788, "dur": 0.373, + "args": { + "External id": 1442918,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854686568.456, "dur": 31.214, + "args": { + "External id": 1442919,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854686651.227, "dur": 124.223, + "args": { + "External id": 1442920,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854686683.281, "dur": 88.888, + "args": { + "External id": 1442921,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8296, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854686692.584, "dur": 75.079, + "args": { + "External id": 1442922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854686792.900, "dur": 2.092, + "args": { + "External id": 1442923,"Record function id": 0, "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": 8298, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854686873.358, "dur": 1792.356, + "args": { + "External id": 1442924,"Sequence number": 15348929, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8299 + } + }, + { + "ph": "f", "id": 406, "pid": 2338706, "tid": 2379422, "ts": 6413854686873.358, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687006.789, "dur": 145.778, + "args": { + "External id": 1442925,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854687203.968, "dur": 44.199, + "args": { + "External id": 1442926,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687267.422, "dur": 53.170, + "args": { + "External id": 1442927,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687330.637, "dur": 31.942, + "args": { + "External id": 1442928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687370.956, "dur": 32.419, + "args": { + "External id": 1442929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687409.953, "dur": 30.551, + "args": { + "External id": 1442930,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687449.123, "dur": 30.224, + "args": { + "External id": 1442931,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854687503.533, "dur": 23.827, + "args": { + "External id": 1442932,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854687547.988, "dur": 27.463, + "args": { + "External id": 1442933,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854687598.973, "dur": 17.175, + "args": { + "External id": 1442934,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854687630.249, "dur": 14.573, + "args": { + "External id": 1442935,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687651.649, "dur": 34.437, + "args": { + "External id": 1442936,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854687689.718, "dur": 32.008, + "args": { + "External id": 1442937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854687755.509, "dur": 260.080, + "args": { + "External id": 1442938,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854687831.363, "dur": 6.151, + "args": { + "External id": 1442939,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854687839.475, "dur": 2.769, + "args": { + "External id": 1442940,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854687843.426, "dur": 1.910, + "args": { + "External id": 1442941,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854687846.319, "dur": 1.968, + "args": { + "External id": 1442942,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854687891.233, "dur": 7.480, + "args": { + "External id": 1442943,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854687895.760, "dur": 2.771, + "args": { + "External id": 1442944,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854687900.929, "dur": 32.110, + "args": { + "External id": 1442945,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854687907.878, "dur": 1.660, + "args": { + "External id": 1442946,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854687934.510, "dur": 1.718, + "args": { + "External id": 1442947,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854687935.444, "dur": 0.696, + "args": { + "External id": 1442948,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854687937.448, "dur": 15.799, + "args": { + "External id": 1442949,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854687939.416, "dur": 2.423, + "args": { + "External id": 1442950,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854688093.345, "dur": 30.888, + "args": { + "External id": 1442951,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854688149.193, "dur": 16.223, + "args": { + "External id": 1442952,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854688174.059, "dur": 46.879, + "args": { + "External id": 1442953,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854688227.847, "dur": 37.983, + "args": { + "External id": 1442954,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854688276.794, "dur": 19.961, + "args": { + "External id": 1442955,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854688302.551, "dur": 46.154, + "args": { + "External id": 1442956,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854688365.125, "dur": 32.792, + "args": { + "External id": 1442957,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854688406.179, "dur": 30.969, + "args": { + "External id": 1442958,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854688463.608, "dur": 24.932, + "args": { + "External id": 1442959,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854688507.808, "dur": 27.602, + "args": { + "External id": 1442960,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854688553.836, "dur": 16.200, + "args": { + "External id": 1442961,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854688588.844, "dur": 13.840, + "args": { + "External id": 1442962,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854688618.192, "dur": 15.147, + "args": { + "External id": 1442963,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688713.631, "dur": 15.434, + "args": { + "External id": 1442964,"Record function id": 0, "Ev Idx": 8339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688717.067, "dur": 10.992, + "args": { + "External id": 1442965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688721.330, "dur": 5.827, + "args": { + "External id": 1442966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688723.000, "dur": 4.057, + "args": { + "External id": 1442967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688733.110, "dur": 5.929, + "args": { + "External id": 1442968,"Record function id": 0, "Ev Idx": 8343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688734.917, "dur": 3.660, + "args": { + "External id": 1442969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688736.077, "dur": 1.773, + "args": { + "External id": 1442970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688736.901, "dur": 0.854, + "args": { + "External id": 1442971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688742.337, "dur": 7.475, + "args": { + "External id": 1442972,"Record function id": 0, "Ev Idx": 8347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688743.734, "dur": 5.632, + "args": { + "External id": 1442973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688744.551, "dur": 4.388, + "args": { + "External id": 1442974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688745.659, "dur": 3.181, + "args": { + "External id": 1442975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688753.042, "dur": 4.940, + "args": { + "External id": 1442976,"Record function id": 0, "Ev Idx": 8351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688754.559, "dur": 2.993, + "args": { + "External id": 1442977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688755.388, "dur": 1.610, + "args": { + "External id": 1442978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688756.034, "dur": 0.898, + "args": { + "External id": 1442979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688761.134, "dur": 4.585, + "args": { + "External id": 1442980,"Record function id": 0, "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688762.806, "dur": 2.506, + "args": { + "External id": 1442981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688763.343, "dur": 1.508, + "args": { + "External id": 1442982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688763.997, "dur": 0.780, + "args": { + "External id": 1442983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688768.911, "dur": 3.991, + "args": { + "External id": 1442984,"Record function id": 0, "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688770.009, "dur": 2.479, + "args": { + "External id": 1442985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688770.830, "dur": 0.929, + "args": { + "External id": 1442986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688771.184, "dur": 0.508, + "args": { + "External id": 1442987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688775.990, "dur": 6.417, + "args": { + "External id": 1442988,"Record function id": 0, "Ev Idx": 8363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688777.349, "dur": 4.625, + "args": { + "External id": 1442989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688777.923, "dur": 3.361, + "args": { + "External id": 1442990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688780.568, "dur": 0.614, + "args": { + "External id": 1442991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688785.541, "dur": 3.724, + "args": { + "External id": 1442992,"Record function id": 0, "Ev Idx": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688786.680, "dur": 2.174, + "args": { + "External id": 1442993,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688787.385, "dur": 1.057, + "args": { + "External id": 1442994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688787.774, "dur": 0.588, + "args": { + "External id": 1442995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688792.473, "dur": 4.485, + "args": { + "External id": 1442996,"Record function id": 0, "Ev Idx": 8371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854688794.090, "dur": 2.437, + "args": { + "External id": 1442997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688794.644, "dur": 1.472, + "args": { + "External id": 1442998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854688795.512, "dur": 0.529, + "args": { + "External id": 1442999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854688800.727, "dur": 64745.122, + "args": { + "External id": 1443000,"Record function id": 0, "Sequence number": 15348928, "Fwd thread id": 1, "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854688802.267, "dur": 64733.568, + "args": { + "External id": 1443001,"Sequence number": 15348928, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8376 + } + }, + { + "ph": "f", "id": 407, "pid": 2338706, "tid": 2379422, "ts": 6413854688802.267, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413854688833.028, "dur": 40.453, + "args": { + "External id": 1443002,"Record function id": 0, "Ev Idx": 8377 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413854688881.061, "dur": 71.061, + "args": { + "External id": 1443003,"Record function id": 0, "Ev Idx": 8378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 2338706, "tid": 2379422, + "ts": 6413854688958.337, "dur": 64569.538, + "args": { + "External id": 1443004,"Record function id": 0, "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854689107.487, "dur": 9.008, + "args": { + "External id": 1443005,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854689127.962, "dur": 7.506, + "args": { + "External id": 1443006,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854689166.499, "dur": 63309.334, + "args": { + "External id": 1443007,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854689183.468, "dur": 63278.827, + "args": { + "External id": 1443008,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854689302.525, "dur": 18.840, + "args": { + "External id": 1443009,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854689341.776, "dur": 63075.126, + "args": { + "External id": 1443010,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854689344.488, "dur": 63071.270, + "args": { + "External id": 1443011,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854689348.400, "dur": 10.488, + "args": { + "External id": 1443012,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854689361.525, "dur": 63049.310, + "args": { + "External id": 1443013,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854752590.993, "dur": 12.627, + "args": { + "External id": 1443014,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854752594.530, "dur": 8.655, + "args": { + "External id": 1443015,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854752633.492, "dur": 500.805, + "args": { + "External id": 1443016,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854752667.099, "dur": 460.921, + "args": { + "External id": 1443017,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8392, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854752679.794, "dur": 439.746, + "args": { + "External id": 1443018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854753160.700, "dur": 2.714, + "args": { + "External id": 1443019,"Record function id": 0, "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": 8394, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753231.684, "dur": 6.976, + "args": { + "External id": 1443020,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753251.177, "dur": 36.426, + "args": { + "External id": 1443021,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753297.983, "dur": 1.730, + "args": { + "External id": 1443022,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753305.809, "dur": 11.518, + "args": { + "External id": 1443023,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753322.787, "dur": 1.326, + "args": { + "External id": 1443024,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753328.834, "dur": 11.389, + "args": { + "External id": 1443025,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753346.406, "dur": 1.024, + "args": { + "External id": 1443026,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753351.582, "dur": 9.850, + "args": { + "External id": 1443027,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753366.308, "dur": 3.641, + "args": { + "External id": 1443028,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753374.640, "dur": 10.649, + "args": { + "External id": 1443029,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753389.583, "dur": 1.457, + "args": { + "External id": 1443030,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753394.961, "dur": 9.844, + "args": { + "External id": 1443031,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753409.195, "dur": 1.139, + "args": { + "External id": 1443032,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753416.474, "dur": 10.840, + "args": { + "External id": 1443033,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753432.169, "dur": 1.036, + "args": { + "External id": 1443034,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753437.703, "dur": 10.325, + "args": { + "External id": 1443035,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753452.260, "dur": 1.007, + "args": { + "External id": 1443036,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753457.223, "dur": 10.500, + "args": { + "External id": 1443037,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854753560.049, "dur": 2985.003, + "args": { + "External id": 1443038,"Record function id": 0, "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413854753581.795, "dur": 1096.710, + "args": { + "External id": 1443039,"Record function id": 0, "Ev Idx": 8414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413854753599.173, "dur": 323.866, + "args": { + "External id": 1443040,"Record function id": 0, "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753687.456, "dur": 3.964, + "args": { + "External id": 1443041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753694.993, "dur": 1.070, + "args": { + "External id": 1443042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753697.834, "dur": 1.111, + "args": { + "External id": 1443043,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753700.651, "dur": 3.031, + "args": { + "External id": 1443044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753707.449, "dur": 1.090, + "args": { + "External id": 1443045,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753710.080, "dur": 0.819, + "args": { + "External id": 1443046,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753712.601, "dur": 0.936, + "args": { + "External id": 1443047,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753715.101, "dur": 1.280, + "args": { + "External id": 1443048,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753720.100, "dur": 1.112, + "args": { + "External id": 1443049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854753722.945, "dur": 0.959, + "args": { + "External id": 1443050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854753742.528, "dur": 151.519, + "args": { + "External id": 1443051,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854753760.050, "dur": 129.598, + "args": { + "External id": 1443052,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854753778.095, "dur": 15.964, + "args": { + "External id": 1443053,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854753797.947, "dur": 65.281, + "args": { + "External id": 1443054,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854753800.963, "dur": 61.941, + "args": { + "External id": 1443055,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854753804.485, "dur": 7.893, + "args": { + "External id": 1443056,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854753815.740, "dur": 46.421, + "args": { + "External id": 1443057,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8432 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 2338706, "tid": 2379422, + "ts": 6413854754035.797, "dur": 635.403, + "args": { + "External id": 1443058,"Record function id": 0, "Ev Idx": 8433 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413854754090.384, "dur": 567.715, + "args": { + "External id": 1443059,"Record function id": 0, "Ev Idx": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854754161.101, "dur": 6.616, + "args": { + "External id": 1443060,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854754185.473, "dur": 30.397, + "args": { + "External id": 1443061,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754190.388, "dur": 1.868, + "args": { + "External id": 1443062,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754193.911, "dur": 1.657, + "args": { + "External id": 1443063,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754196.720, "dur": 0.610, + "args": { + "External id": 1443064,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754198.169, "dur": 0.733, + "args": { + "External id": 1443065,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754200.986, "dur": 0.522, + "args": { + "External id": 1443066,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754202.731, "dur": 0.779, + "args": { + "External id": 1443067,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754204.983, "dur": 2.510, + "args": { + "External id": 1443068,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754209.665, "dur": 0.609, + "args": { + "External id": 1443069,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754211.346, "dur": 0.588, + "args": { + "External id": 1443070,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854754228.288, "dur": 48.307, + "args": { + "External id": 1443071,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854754308.054, "dur": 109.980, + "args": { + "External id": 1443072,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854754318.596, "dur": 3.250, + "args": { + "External id": 1443073,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854754326.802, "dur": 10.500, + "args": { + "External id": 1443074,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854754331.469, "dur": 5.385, + "args": { + "External id": 1443075,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754335.033, "dur": 0.590, + "args": { + "External id": 1443076,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854754343.735, "dur": 25.401, + "args": { + "External id": 1443077,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754346.357, "dur": 0.735, + "args": { + "External id": 1443078,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754349.350, "dur": 0.452, + "args": { + "External id": 1443079,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754350.785, "dur": 0.388, + "args": { + "External id": 1443080,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754352.236, "dur": 3.735, + "args": { + "External id": 1443081,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754357.120, "dur": 0.349, + "args": { + "External id": 1443082,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754358.616, "dur": 0.412, + "args": { + "External id": 1443083,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754361.869, "dur": 0.396, + "args": { + "External id": 1443084,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754363.532, "dur": 0.647, + "args": { + "External id": 1443085,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854754365.345, "dur": 0.555, + "args": { + "External id": 1443086,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854754380.180, "dur": 30.772, + "args": { + "External id": 1443087,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854754464.593, "dur": 121.677, + "args": { + "External id": 1443088,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854754494.552, "dur": 88.646, + "args": { + "External id": 1443089,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8464, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854754504.737, "dur": 74.445, + "args": { + "External id": 1443090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854754606.125, "dur": 2.256, + "args": { + "External id": 1443091,"Record function id": 0, "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": 8466, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854754685.871, "dur": 1832.812, + "args": { + "External id": 1443092,"Sequence number": 15348927, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8467 + } + }, + { + "ph": "f", "id": 408, "pid": 2338706, "tid": 2379422, "ts": 6413854754685.871, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854754797.704, "dur": 103.161, + "args": { + "External id": 1443093,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854754946.570, "dur": 64.588, + "args": { + "External id": 1443094,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755033.810, "dur": 93.473, + "args": { + "External id": 1443095,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755142.364, "dur": 34.191, + "args": { + "External id": 1443096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755186.350, "dur": 33.125, + "args": { + "External id": 1443097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755226.922, "dur": 27.389, + "args": { + "External id": 1443098,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755261.587, "dur": 28.946, + "args": { + "External id": 1443099,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854755319.432, "dur": 27.048, + "args": { + "External id": 1443100,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854755369.221, "dur": 28.417, + "args": { + "External id": 1443101,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854755421.053, "dur": 19.611, + "args": { + "External id": 1443102,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854755456.079, "dur": 17.217, + "args": { + "External id": 1443103,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755481.153, "dur": 36.478, + "args": { + "External id": 1443104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755521.337, "dur": 32.375, + "args": { + "External id": 1443105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854755585.897, "dur": 253.492, + "args": { + "External id": 1443106,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854755665.017, "dur": 6.652, + "args": { + "External id": 1443107,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854755673.490, "dur": 3.392, + "args": { + "External id": 1443108,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854755677.918, "dur": 2.883, + "args": { + "External id": 1443109,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854755681.772, "dur": 3.682, + "args": { + "External id": 1443110,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854755732.039, "dur": 4.883, + "args": { + "External id": 1443111,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854755733.932, "dur": 2.832, + "args": { + "External id": 1443112,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854755739.215, "dur": 32.948, + "args": { + "External id": 1443113,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854755746.589, "dur": 1.764, + "args": { + "External id": 1443114,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854755775.826, "dur": 1.946, + "args": { + "External id": 1443115,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854755776.982, "dur": 0.714, + "args": { + "External id": 1443116,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854755779.349, "dur": 16.063, + "args": { + "External id": 1443117,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854755781.137, "dur": 2.696, + "args": { + "External id": 1443118,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854755879.583, "dur": 27.183, + "args": { + "External id": 1443119,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854755925.451, "dur": 16.079, + "args": { + "External id": 1443120,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854755948.701, "dur": 58.877, + "args": { + "External id": 1443121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854756017.148, "dur": 93.258, + "args": { + "External id": 1443122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854756135.278, "dur": 32.444, + "args": { + "External id": 1443123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854756176.710, "dur": 33.268, + "args": { + "External id": 1443124,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854756221.282, "dur": 28.889, + "args": { + "External id": 1443125,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854756256.955, "dur": 31.606, + "args": { + "External id": 1443126,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854756316.887, "dur": 26.440, + "args": { + "External id": 1443127,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854756364.351, "dur": 24.493, + "args": { + "External id": 1443128,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854756408.476, "dur": 16.873, + "args": { + "External id": 1443129,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854756439.597, "dur": 13.799, + "args": { + "External id": 1443130,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854756470.133, "dur": 15.541, + "args": { + "External id": 1443131,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756568.402, "dur": 16.845, + "args": { + "External id": 1443132,"Record function id": 0, "Ev Idx": 8507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756571.542, "dur": 12.806, + "args": { + "External id": 1443133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756576.147, "dur": 7.242, + "args": { + "External id": 1443134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756579.223, "dur": 4.047, + "args": { + "External id": 1443135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756589.338, "dur": 5.120, + "args": { + "External id": 1443136,"Record function id": 0, "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756590.500, "dur": 3.462, + "args": { + "External id": 1443137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756591.760, "dur": 1.660, + "args": { + "External id": 1443138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756592.446, "dur": 0.874, + "args": { + "External id": 1443139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756600.998, "dur": 4.613, + "args": { + "External id": 1443140,"Record function id": 0, "Ev Idx": 8515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756602.509, "dur": 2.671, + "args": { + "External id": 1443141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756603.336, "dur": 1.411, + "args": { + "External id": 1443142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756604.080, "dur": 0.562, + "args": { + "External id": 1443143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756608.834, "dur": 4.216, + "args": { + "External id": 1443144,"Record function id": 0, "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756610.224, "dur": 2.432, + "args": { + "External id": 1443145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756610.949, "dur": 1.272, + "args": { + "External id": 1443146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756611.543, "dur": 0.602, + "args": { + "External id": 1443147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756616.176, "dur": 3.850, + "args": { + "External id": 1443148,"Record function id": 0, "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756617.152, "dur": 2.481, + "args": { + "External id": 1443149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756617.887, "dur": 1.157, + "args": { + "External id": 1443150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756618.189, "dur": 0.780, + "args": { + "External id": 1443151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756623.122, "dur": 6.472, + "args": { + "External id": 1443152,"Record function id": 0, "Ev Idx": 8527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756624.509, "dur": 4.641, + "args": { + "External id": 1443153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756624.949, "dur": 3.749, + "args": { + "External id": 1443154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756625.630, "dur": 2.995, + "args": { + "External id": 1443155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756632.776, "dur": 3.580, + "args": { + "External id": 1443156,"Record function id": 0, "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756633.785, "dur": 2.166, + "args": { + "External id": 1443157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756634.223, "dur": 1.312, + "args": { + "External id": 1443158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756634.509, "dur": 0.959, + "args": { + "External id": 1443159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756639.451, "dur": 30.298, + "args": { + "External id": 1443160,"Record function id": 0, "Ev Idx": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756666.979, "dur": 2.237, + "args": { + "External id": 1443161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756667.733, "dur": 1.044, + "args": { + "External id": 1443162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756668.049, "dur": 0.664, + "args": { + "External id": 1443163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756673.560, "dur": 6.009, + "args": { + "External id": 1443164,"Record function id": 0, "Ev Idx": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854756674.604, "dur": 4.549, + "args": { + "External id": 1443165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756675.311, "dur": 3.374, + "args": { + "External id": 1443166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854756677.866, "dur": 0.744, + "args": { + "External id": 1443167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854756684.325, "dur": 65955.224, + "args": { + "External id": 1443168,"Record function id": 0, "Sequence number": 15348926, "Fwd thread id": 1, "Ev Idx": 8543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854756716.558, "dur": 65913.306, + "args": { + "External id": 1443169,"Sequence number": 15348926, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8544 + } + }, + { + "ph": "f", "id": 409, "pid": 2338706, "tid": 2379422, "ts": 6413854756716.558, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413854756748.319, "dur": 41.681, + "args": { + "External id": 1443170,"Record function id": 0, "Ev Idx": 8545 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413854756797.503, "dur": 71.740, + "args": { + "External id": 1443171,"Record function id": 0, "Ev Idx": 8546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 2338706, "tid": 2379422, + "ts": 6413854756874.865, "dur": 65747.219, + "args": { + "External id": 1443172,"Record function id": 0, "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854756967.226, "dur": 7.347, + "args": { + "External id": 1443173,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854757004.693, "dur": 5.317, + "args": { + "External id": 1443174,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854757026.632, "dur": 64620.468, + "args": { + "External id": 1443175,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854757043.111, "dur": 64590.755, + "args": { + "External id": 1443176,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854757196.588, "dur": 21.798, + "args": { + "External id": 1443177,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854757238.451, "dur": 64347.589, + "args": { + "External id": 1443178,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854757244.368, "dur": 64340.396, + "args": { + "External id": 1443179,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854757249.112, "dur": 12.792, + "args": { + "External id": 1443180,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854757264.029, "dur": 64315.533, + "args": { + "External id": 1443181,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854821761.304, "dur": 13.354, + "args": { + "External id": 1443182,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854821765.119, "dur": 9.080, + "args": { + "External id": 1443183,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854821805.980, "dur": 427.065, + "args": { + "External id": 1443184,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854821841.530, "dur": 385.964, + "args": { + "External id": 1443185,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8560, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854821854.824, "dur": 366.717, + "args": { + "External id": 1443186,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854822258.412, "dur": 2.289, + "args": { + "External id": 1443187,"Record function id": 0, "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": 8562, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822326.104, "dur": 7.219, + "args": { + "External id": 1443188,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822346.074, "dur": 34.407, + "args": { + "External id": 1443189,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822390.629, "dur": 3.619, + "args": { + "External id": 1443190,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822400.837, "dur": 11.918, + "args": { + "External id": 1443191,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822418.649, "dur": 1.155, + "args": { + "External id": 1443192,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822424.399, "dur": 11.340, + "args": { + "External id": 1443193,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822440.736, "dur": 1.084, + "args": { + "External id": 1443194,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822446.204, "dur": 9.712, + "args": { + "External id": 1443195,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822463.149, "dur": 0.964, + "args": { + "External id": 1443196,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822468.389, "dur": 11.379, + "args": { + "External id": 1443197,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822483.881, "dur": 1.944, + "args": { + "External id": 1443198,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822489.783, "dur": 9.758, + "args": { + "External id": 1443199,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822504.539, "dur": 1.144, + "args": { + "External id": 1443200,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822509.728, "dur": 10.773, + "args": { + "External id": 1443201,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822526.654, "dur": 1.247, + "args": { + "External id": 1443202,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822531.954, "dur": 10.562, + "args": { + "External id": 1443203,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822546.519, "dur": 0.918, + "args": { + "External id": 1443204,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822551.510, "dur": 10.740, + "args": { + "External id": 1443205,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854822654.218, "dur": 2989.226, + "args": { + "External id": 1443206,"Record function id": 0, "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413854822676.088, "dur": 1098.665, + "args": { + "External id": 1443207,"Record function id": 0, "Ev Idx": 8582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413854822691.810, "dur": 345.039, + "args": { + "External id": 1443208,"Record function id": 0, "Ev Idx": 8583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822780.564, "dur": 6.787, + "args": { + "External id": 1443209,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822790.228, "dur": 0.914, + "args": { + "External id": 1443210,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822793.207, "dur": 0.878, + "args": { + "External id": 1443211,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822795.834, "dur": 1.033, + "args": { + "External id": 1443212,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822798.256, "dur": 1.118, + "args": { + "External id": 1443213,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822803.099, "dur": 1.102, + "args": { + "External id": 1443214,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822805.692, "dur": 0.780, + "args": { + "External id": 1443215,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822807.865, "dur": 1.285, + "args": { + "External id": 1443216,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822810.899, "dur": 3.084, + "args": { + "External id": 1443217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854822817.406, "dur": 0.889, + "args": { + "External id": 1443218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854822836.350, "dur": 166.489, + "args": { + "External id": 1443219,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854822854.264, "dur": 122.565, + "args": { + "External id": 1443220,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854822871.314, "dur": 14.199, + "args": { + "External id": 1443221,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854822889.219, "dur": 61.729, + "args": { + "External id": 1443222,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854822891.898, "dur": 58.671, + "args": { + "External id": 1443223,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854822895.483, "dur": 5.374, + "args": { + "External id": 1443224,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854822902.436, "dur": 47.421, + "args": { + "External id": 1443225,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8600 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 2338706, "tid": 2379422, + "ts": 6413854823172.670, "dur": 594.411, + "args": { + "External id": 1443226,"Record function id": 0, "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413854823192.426, "dur": 561.766, + "args": { + "External id": 1443227,"Record function id": 0, "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854823259.405, "dur": 6.705, + "args": { + "External id": 1443228,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854823283.266, "dur": 30.081, + "args": { + "External id": 1443229,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823288.229, "dur": 1.767, + "args": { + "External id": 1443230,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823291.526, "dur": 1.544, + "args": { + "External id": 1443231,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823294.216, "dur": 0.657, + "args": { + "External id": 1443232,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823296.422, "dur": 2.684, + "args": { + "External id": 1443233,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823301.693, "dur": 0.339, + "args": { + "External id": 1443234,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823303.277, "dur": 0.656, + "args": { + "External id": 1443235,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823305.126, "dur": 0.620, + "args": { + "External id": 1443236,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823308.098, "dur": 0.403, + "args": { + "External id": 1443237,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823309.609, "dur": 0.345, + "args": { + "External id": 1443238,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854823324.626, "dur": 46.532, + "args": { + "External id": 1443239,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854823401.557, "dur": 116.160, + "args": { + "External id": 1443240,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854823411.848, "dur": 3.646, + "args": { + "External id": 1443241,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854823420.851, "dur": 13.000, + "args": { + "External id": 1443242,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854823427.653, "dur": 5.735, + "args": { + "External id": 1443243,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823431.197, "dur": 0.676, + "args": { + "External id": 1443244,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854823440.368, "dur": 29.842, + "args": { + "External id": 1443245,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823442.562, "dur": 2.918, + "args": { + "External id": 1443246,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823448.215, "dur": 0.345, + "args": { + "External id": 1443247,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823449.905, "dur": 0.480, + "args": { + "External id": 1443248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823451.528, "dur": 1.841, + "args": { + "External id": 1443249,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823454.497, "dur": 0.690, + "args": { + "External id": 1443250,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823456.483, "dur": 0.650, + "args": { + "External id": 1443251,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823460.075, "dur": 0.272, + "args": { + "External id": 1443252,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823461.565, "dur": 0.561, + "args": { + "External id": 1443253,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854823463.828, "dur": 2.755, + "args": { + "External id": 1443254,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854823481.102, "dur": 29.262, + "args": { + "External id": 1443255,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854823561.597, "dur": 123.554, + "args": { + "External id": 1443256,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854823592.503, "dur": 89.104, + "args": { + "External id": 1443257,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8632, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854823602.174, "dur": 74.648, + "args": { + "External id": 1443258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854823702.740, "dur": 1.940, + "args": { + "External id": 1443259,"Record function id": 0, "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": 8634, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854823781.784, "dur": 1837.137, + "args": { + "External id": 1443260,"Sequence number": 15348925, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8635 + } + }, + { + "ph": "f", "id": 410, "pid": 2338706, "tid": 2379422, "ts": 6413854823781.784, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854823892.591, "dur": 126.512, + "args": { + "External id": 1443261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854824103.194, "dur": 44.949, + "args": { + "External id": 1443262,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824172.095, "dur": 59.103, + "args": { + "External id": 1443263,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824242.106, "dur": 32.877, + "args": { + "External id": 1443264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824281.432, "dur": 33.254, + "args": { + "External id": 1443265,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824321.831, "dur": 28.606, + "args": { + "External id": 1443266,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824361.046, "dur": 30.302, + "args": { + "External id": 1443267,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854824418.977, "dur": 25.698, + "args": { + "External id": 1443268,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854824469.894, "dur": 30.385, + "args": { + "External id": 1443269,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854824526.605, "dur": 20.203, + "args": { + "External id": 1443270,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854824565.654, "dur": 16.078, + "args": { + "External id": 1443271,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824591.737, "dur": 35.959, + "args": { + "External id": 1443272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854824630.814, "dur": 32.503, + "args": { + "External id": 1443273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854824694.379, "dur": 246.078, + "args": { + "External id": 1443274,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854824773.286, "dur": 6.156, + "args": { + "External id": 1443275,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854824781.540, "dur": 2.976, + "args": { + "External id": 1443276,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854824785.536, "dur": 2.472, + "args": { + "External id": 1443277,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854824789.149, "dur": 5.148, + "args": { + "External id": 1443278,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854824838.375, "dur": 4.578, + "args": { + "External id": 1443279,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854824840.076, "dur": 2.700, + "args": { + "External id": 1443280,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854824845.300, "dur": 31.926, + "args": { + "External id": 1443281,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854824852.557, "dur": 1.698, + "args": { + "External id": 1443282,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854824879.046, "dur": 1.845, + "args": { + "External id": 1443283,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854824880.087, "dur": 0.712, + "args": { + "External id": 1443284,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854824881.766, "dur": 14.123, + "args": { + "External id": 1443285,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854824883.665, "dur": 0.652, + "args": { + "External id": 1443286,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854824999.830, "dur": 29.716, + "args": { + "External id": 1443287,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854825051.750, "dur": 54.143, + "args": { + "External id": 1443288,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854825117.786, "dur": 51.687, + "args": { + "External id": 1443289,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854825176.696, "dur": 40.744, + "args": { + "External id": 1443290,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854825225.756, "dur": 38.062, + "args": { + "External id": 1443291,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854825279.955, "dur": 35.097, + "args": { + "External id": 1443292,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854825323.093, "dur": 27.242, + "args": { + "External id": 1443293,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854825357.234, "dur": 33.383, + "args": { + "External id": 1443294,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854825416.275, "dur": 27.638, + "args": { + "External id": 1443295,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854825461.529, "dur": 24.831, + "args": { + "External id": 1443296,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854825505.192, "dur": 18.132, + "args": { + "External id": 1443297,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854825539.682, "dur": 14.455, + "args": { + "External id": 1443298,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854825569.100, "dur": 17.683, + "args": { + "External id": 1443299,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825666.484, "dur": 16.759, + "args": { + "External id": 1443300,"Record function id": 0, "Ev Idx": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825670.084, "dur": 12.277, + "args": { + "External id": 1443301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825674.611, "dur": 6.947, + "args": { + "External id": 1443302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825677.603, "dur": 3.850, + "args": { + "External id": 1443303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825687.244, "dur": 5.605, + "args": { + "External id": 1443304,"Record function id": 0, "Ev Idx": 8679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825689.038, "dur": 3.284, + "args": { + "External id": 1443305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825690.056, "dur": 1.627, + "args": { + "External id": 1443306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825690.700, "dur": 0.888, + "args": { + "External id": 1443307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825696.063, "dur": 4.823, + "args": { + "External id": 1443308,"Record function id": 0, "Ev Idx": 8683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825697.618, "dur": 2.830, + "args": { + "External id": 1443309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825698.369, "dur": 1.675, + "args": { + "External id": 1443310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825699.221, "dur": 0.707, + "args": { + "External id": 1443311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825704.068, "dur": 4.275, + "args": { + "External id": 1443312,"Record function id": 0, "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825705.483, "dur": 2.424, + "args": { + "External id": 1443313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825706.181, "dur": 1.292, + "args": { + "External id": 1443314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825706.811, "dur": 0.588, + "args": { + "External id": 1443315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825711.436, "dur": 21.093, + "args": { + "External id": 1443316,"Record function id": 0, "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825729.361, "dur": 2.691, + "args": { + "External id": 1443317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825730.367, "dur": 1.155, + "args": { + "External id": 1443318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825730.653, "dur": 0.740, + "args": { + "External id": 1443319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825735.808, "dur": 8.742, + "args": { + "External id": 1443320,"Record function id": 0, "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825736.893, "dur": 7.197, + "args": { + "External id": 1443321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825737.473, "dur": 6.027, + "args": { + "External id": 1443322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825740.363, "dur": 3.053, + "args": { + "External id": 1443323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825747.978, "dur": 5.009, + "args": { + "External id": 1443324,"Record function id": 0, "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825749.565, "dur": 3.011, + "args": { + "External id": 1443325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825750.755, "dur": 1.428, + "args": { + "External id": 1443326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825751.362, "dur": 0.747, + "args": { + "External id": 1443327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825756.046, "dur": 71.300, + "args": { + "External id": 1443328,"Record function id": 0, "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825823.777, "dur": 3.028, + "args": { + "External id": 1443329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825824.703, "dur": 1.597, + "args": { + "External id": 1443330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825825.136, "dur": 1.063, + "args": { + "External id": 1443331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825830.898, "dur": 6.591, + "args": { + "External id": 1443332,"Record function id": 0, "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854825832.708, "dur": 4.325, + "args": { + "External id": 1443333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825833.261, "dur": 3.328, + "args": { + "External id": 1443334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854825835.897, "dur": 0.596, + "args": { + "External id": 1443335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854825841.983, "dur": 65169.610, + "args": { + "External id": 1443336,"Record function id": 0, "Sequence number": 15348924, "Fwd thread id": 1, "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854825843.488, "dur": 65157.318, + "args": { + "External id": 1443337,"Sequence number": 15348924, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8712 + } + }, + { + "ph": "f", "id": 411, "pid": 2338706, "tid": 2379422, "ts": 6413854825843.488, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413854825875.754, "dur": 41.638, + "args": { + "External id": 1443338,"Record function id": 0, "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413854825925.820, "dur": 91.874, + "args": { + "External id": 1443339,"Record function id": 0, "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 2338706, "tid": 2379422, + "ts": 6413854826025.794, "dur": 64948.172, + "args": { + "External id": 1443340,"Record function id": 0, "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854826164.329, "dur": 8.154, + "args": { + "External id": 1443341,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854826188.443, "dur": 5.048, + "args": { + "External id": 1443342,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854826208.520, "dur": 63793.784, + "args": { + "External id": 1443343,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854826223.386, "dur": 63764.586, + "args": { + "External id": 1443344,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854826368.265, "dur": 19.656, + "args": { + "External id": 1443345,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854826407.781, "dur": 63522.608, + "args": { + "External id": 1443346,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854826410.763, "dur": 63518.479, + "args": { + "External id": 1443347,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854826415.506, "dur": 8.778, + "args": { + "External id": 1443348,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854826427.011, "dur": 63497.430, + "args": { + "External id": 1443349,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854890150.432, "dur": 13.885, + "args": { + "External id": 1443350,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854890154.373, "dur": 9.386, + "args": { + "External id": 1443351,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890193.581, "dur": 388.621, + "args": { + "External id": 1443352,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854890228.152, "dur": 349.003, + "args": { + "External id": 1443353,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8728, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854890241.283, "dur": 330.186, + "args": { + "External id": 1443354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854890605.592, "dur": 2.062, + "args": { + "External id": 1443355,"Record function id": 0, "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": 8730, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890667.390, "dur": 6.535, + "args": { + "External id": 1443356,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890687.402, "dur": 35.015, + "args": { + "External id": 1443357,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890733.284, "dur": 3.245, + "args": { + "External id": 1443358,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890742.780, "dur": 13.252, + "args": { + "External id": 1443359,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890761.640, "dur": 0.819, + "args": { + "External id": 1443360,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890766.526, "dur": 12.671, + "args": { + "External id": 1443361,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890785.515, "dur": 0.884, + "args": { + "External id": 1443362,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890790.989, "dur": 11.048, + "args": { + "External id": 1443363,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890807.117, "dur": 0.754, + "args": { + "External id": 1443364,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890812.144, "dur": 12.551, + "args": { + "External id": 1443365,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890829.056, "dur": 1.764, + "args": { + "External id": 1443366,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890834.750, "dur": 11.916, + "args": { + "External id": 1443367,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890853.175, "dur": 0.632, + "args": { + "External id": 1443368,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890856.914, "dur": 12.400, + "args": { + "External id": 1443369,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890873.671, "dur": 0.650, + "args": { + "External id": 1443370,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890878.307, "dur": 11.119, + "args": { + "External id": 1443371,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854890894.487, "dur": 6.070, + "args": { + "External id": 1443372,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854890904.892, "dur": 12.179, + "args": { + "External id": 1443373,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854891028.373, "dur": 3926.526, + "args": { + "External id": 1443374,"Record function id": 0, "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413854891051.514, "dur": 1448.509, + "args": { + "External id": 1443375,"Record function id": 0, "Ev Idx": 8750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413854891102.329, "dur": 343.471, + "args": { + "External id": 1443376,"Record function id": 0, "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891197.181, "dur": 7.341, + "args": { + "External id": 1443377,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891207.645, "dur": 1.121, + "args": { + "External id": 1443378,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891210.679, "dur": 1.193, + "args": { + "External id": 1443379,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891213.385, "dur": 1.244, + "args": { + "External id": 1443380,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891225.109, "dur": 0.979, + "args": { + "External id": 1443381,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891227.649, "dur": 1.064, + "args": { + "External id": 1443382,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891230.666, "dur": 1.015, + "args": { + "External id": 1443383,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891233.196, "dur": 0.924, + "args": { + "External id": 1443384,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891237.631, "dur": 2.920, + "args": { + "External id": 1443385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854891242.155, "dur": 0.997, + "args": { + "External id": 1443386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854891261.499, "dur": 151.831, + "args": { + "External id": 1443387,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854891279.351, "dur": 129.288, + "args": { + "External id": 1443388,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854891295.685, "dur": 14.365, + "args": { + "External id": 1443389,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854891313.734, "dur": 67.444, + "args": { + "External id": 1443390,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854891318.578, "dur": 62.226, + "args": { + "External id": 1443391,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891322.234, "dur": 5.547, + "args": { + "External id": 1443392,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854891329.564, "dur": 50.691, + "args": { + "External id": 1443393,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8768 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 2338706, "tid": 2379422, + "ts": 6413854891534.929, "dur": 951.056, + "args": { + "External id": 1443394,"Record function id": 0, "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413854891552.524, "dur": 908.234, + "args": { + "External id": 1443395,"Record function id": 0, "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854891615.077, "dur": 5.042, + "args": { + "External id": 1443396,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854891637.022, "dur": 34.110, + "args": { + "External id": 1443397,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891642.498, "dur": 1.787, + "args": { + "External id": 1443398,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891646.576, "dur": 2.313, + "args": { + "External id": 1443399,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891650.370, "dur": 0.647, + "args": { + "External id": 1443400,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891652.306, "dur": 2.463, + "args": { + "External id": 1443401,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891657.896, "dur": 0.416, + "args": { + "External id": 1443402,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891659.788, "dur": 0.489, + "args": { + "External id": 1443403,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891661.776, "dur": 0.907, + "args": { + "External id": 1443404,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891665.607, "dur": 0.745, + "args": { + "External id": 1443405,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891667.368, "dur": 0.777, + "args": { + "External id": 1443406,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854891683.444, "dur": 42.741, + "args": { + "External id": 1443407,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854891757.226, "dur": 111.033, + "args": { + "External id": 1443408,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854891767.173, "dur": 3.207, + "args": { + "External id": 1443409,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854891775.924, "dur": 10.567, + "args": { + "External id": 1443410,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854891780.349, "dur": 5.697, + "args": { + "External id": 1443411,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891784.020, "dur": 0.927, + "args": { + "External id": 1443412,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854891792.364, "dur": 27.304, + "args": { + "External id": 1443413,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891794.537, "dur": 2.762, + "args": { + "External id": 1443414,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891799.490, "dur": 0.616, + "args": { + "External id": 1443415,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891801.300, "dur": 0.680, + "args": { + "External id": 1443416,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891803.057, "dur": 1.395, + "args": { + "External id": 1443417,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891805.477, "dur": 0.251, + "args": { + "External id": 1443418,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891806.948, "dur": 0.591, + "args": { + "External id": 1443419,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891810.405, "dur": 0.228, + "args": { + "External id": 1443420,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891811.863, "dur": 0.543, + "args": { + "External id": 1443421,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854891813.830, "dur": 2.651, + "args": { + "External id": 1443422,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854891829.908, "dur": 30.918, + "args": { + "External id": 1443423,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854891912.506, "dur": 248.715, + "args": { + "External id": 1443424,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854891942.357, "dur": 108.463, + "args": { + "External id": 1443425,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8800, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854891951.366, "dur": 94.797, + "args": { + "External id": 1443426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854892243.019, "dur": 22.892, + "args": { + "External id": 1443427,"Record function id": 0, "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": 8802, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854892514.909, "dur": 2406.884, + "args": { + "External id": 1443428,"Sequence number": 15348923, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8803 + } + }, + { + "ph": "f", "id": 412, "pid": 2338706, "tid": 2379422, "ts": 6413854892514.909, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854892693.056, "dur": 168.838, + "args": { + "External id": 1443429,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854892929.436, "dur": 81.103, + "args": { + "External id": 1443430,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893044.785, "dur": 127.952, + "args": { + "External id": 1443431,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893197.953, "dur": 44.600, + "args": { + "External id": 1443432,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893250.587, "dur": 40.493, + "args": { + "External id": 1443433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893299.375, "dur": 32.958, + "args": { + "External id": 1443434,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893344.729, "dur": 36.258, + "args": { + "External id": 1443435,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854893422.993, "dur": 38.882, + "args": { + "External id": 1443436,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854893488.617, "dur": 40.914, + "args": { + "External id": 1443437,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854893561.378, "dur": 25.688, + "args": { + "External id": 1443438,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854893627.632, "dur": 27.240, + "args": { + "External id": 1443439,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893671.023, "dur": 47.688, + "args": { + "External id": 1443440,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854893722.998, "dur": 40.431, + "args": { + "External id": 1443441,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854893807.068, "dur": 406.567, + "args": { + "External id": 1443442,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854893926.199, "dur": 9.881, + "args": { + "External id": 1443443,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854893938.661, "dur": 4.110, + "args": { + "External id": 1443444,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854893944.683, "dur": 3.283, + "args": { + "External id": 1443445,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854893949.131, "dur": 5.857, + "args": { + "External id": 1443446,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854894033.987, "dur": 7.117, + "args": { + "External id": 1443447,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854894036.636, "dur": 3.991, + "args": { + "External id": 1443448,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854894044.173, "dur": 79.847, + "args": { + "External id": 1443449,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854894053.668, "dur": 36.744, + "args": { + "External id": 1443450,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854894130.147, "dur": 2.714, + "args": { + "External id": 1443451,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854894131.558, "dur": 1.132, + "args": { + "External id": 1443452,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854894134.370, "dur": 18.227, + "args": { + "External id": 1443453,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854894137.984, "dur": 0.755, + "args": { + "External id": 1443454,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854894269.327, "dur": 38.093, + "args": { + "External id": 1443455,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854894331.749, "dur": 24.118, + "args": { + "External id": 1443456,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854894364.781, "dur": 62.763, + "args": { + "External id": 1443457,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854894435.003, "dur": 50.455, + "args": { + "External id": 1443458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854894495.204, "dur": 26.152, + "args": { + "External id": 1443459,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 8834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854894530.781, "dur": 36.531, + "args": { + "External id": 1443460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 8835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854894575.771, "dur": 31.554, + "args": { + "External id": 1443461,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854894614.935, "dur": 35.212, + "args": { + "External id": 1443462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854894680.157, "dur": 28.166, + "args": { + "External id": 1443463,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 8838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854894733.176, "dur": 29.304, + "args": { + "External id": 1443464,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854894786.486, "dur": 19.297, + "args": { + "External id": 1443465,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854894822.666, "dur": 15.917, + "args": { + "External id": 1443466,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854894860.880, "dur": 19.839, + "args": { + "External id": 1443467,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 8842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895003.322, "dur": 50.908, + "args": { + "External id": 1443468,"Record function id": 0, "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895009.547, "dur": 42.782, + "args": { + "External id": 1443469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895039.097, "dur": 11.345, + "args": { + "External id": 1443470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895044.902, "dur": 5.211, + "args": { + "External id": 1443471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895102.324, "dur": 9.156, + "args": { + "External id": 1443472,"Record function id": 0, "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895104.898, "dur": 5.681, + "args": { + "External id": 1443473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895106.557, "dur": 2.774, + "args": { + "External id": 1443474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895107.198, "dur": 1.907, + "args": { + "External id": 1443475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895115.653, "dur": 8.581, + "args": { + "External id": 1443476,"Record function id": 0, "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895117.038, "dur": 6.527, + "args": { + "External id": 1443477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895117.983, "dur": 4.941, + "args": { + "External id": 1443478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895121.858, "dur": 0.933, + "args": { + "External id": 1443479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 8854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895128.176, "dur": 5.463, + "args": { + "External id": 1443480,"Record function id": 0, "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895129.603, "dur": 3.547, + "args": { + "External id": 1443481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895130.591, "dur": 1.883, + "args": { + "External id": 1443482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895131.518, "dur": 0.877, + "args": { + "External id": 1443483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 8858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895137.503, "dur": 5.301, + "args": { + "External id": 1443484,"Record function id": 0, "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895138.946, "dur": 3.347, + "args": { + "External id": 1443485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895139.703, "dur": 2.076, + "args": { + "External id": 1443486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895140.819, "dur": 0.838, + "args": { + "External id": 1443487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895146.476, "dur": 10.206, + "args": { + "External id": 1443488,"Record function id": 0, "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895147.838, "dur": 8.355, + "args": { + "External id": 1443489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895148.402, "dur": 7.211, + "args": { + "External id": 1443490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895152.099, "dur": 3.435, + "args": { + "External id": 1443491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 8866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895160.558, "dur": 8.174, + "args": { + "External id": 1443492,"Record function id": 0, "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895162.062, "dur": 6.204, + "args": { + "External id": 1443493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895162.975, "dur": 4.646, + "args": { + "External id": 1443494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895166.508, "dur": 1.039, + "args": { + "External id": 1443495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895172.460, "dur": 4.479, + "args": { + "External id": 1443496,"Record function id": 0, "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895173.910, "dur": 2.569, + "args": { + "External id": 1443497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895174.438, "dur": 1.522, + "args": { + "External id": 1443498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895174.979, "dur": 0.904, + "args": { + "External id": 1443499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 8874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895180.513, "dur": 4.705, + "args": { + "External id": 1443500,"Record function id": 0, "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854895182.344, "dur": 2.395, + "args": { + "External id": 1443501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895182.983, "dur": 1.233, + "args": { + "External id": 1443502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854895183.470, "dur": 0.664, + "args": { + "External id": 1443503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 8878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854895190.139, "dur": 65517.498, + "args": { + "External id": 1443504,"Record function id": 0, "Sequence number": 15348922, "Fwd thread id": 1, "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854895191.809, "dur": 65506.102, + "args": { + "External id": 1443505,"Sequence number": 15348922, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8880 + } + }, + { + "ph": "f", "id": 413, "pid": 2338706, "tid": 2379422, "ts": 6413854895191.809, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413854895234.268, "dur": 52.482, + "args": { + "External id": 1443506,"Record function id": 0, "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413854895299.708, "dur": 112.720, + "args": { + "External id": 1443507,"Record function id": 0, "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 2338706, "tid": 2379422, + "ts": 6413854895424.439, "dur": 65263.693, + "args": { + "External id": 1443508,"Record function id": 0, "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854895560.690, "dur": 9.434, + "args": { + "External id": 1443509,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854895584.664, "dur": 5.750, + "args": { + "External id": 1443510,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854895612.378, "dur": 64014.503, + "args": { + "External id": 1443511,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854895630.240, "dur": 63979.377, + "args": { + "External id": 1443512,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 8887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854895855.155, "dur": 22.814, + "args": { + "External id": 1443513,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854895925.005, "dur": 63629.882, + "args": { + "External id": 1443514,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 8889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854895929.488, "dur": 63623.847, + "args": { + "External id": 1443515,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 8890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854895963.763, "dur": 11.808, + "args": { + "External id": 1443516,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854895999.896, "dur": 63546.955, + "args": { + "External id": 1443517,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 8892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854959761.858, "dur": 14.773, + "args": { + "External id": 1443518,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 8893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854959765.824, "dur": 10.308, + "args": { + "External id": 1443519,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854959807.297, "dur": 466.293, + "args": { + "External id": 1443520,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 8895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854959840.379, "dur": 427.184, + "args": { + "External id": 1443521,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8896, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854959853.360, "dur": 407.641, + "args": { + "External id": 1443522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 8897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854960300.870, "dur": 2.922, + "args": { + "External id": 1443523,"Record function id": 0, "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": 8898, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960368.597, "dur": 7.143, + "args": { + "External id": 1443524,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960389.052, "dur": 35.117, + "args": { + "External id": 1443525,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960435.505, "dur": 3.774, + "args": { + "External id": 1443526,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960444.830, "dur": 13.674, + "args": { + "External id": 1443527,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960464.895, "dur": 0.977, + "args": { + "External id": 1443528,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960471.084, "dur": 12.641, + "args": { + "External id": 1443529,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960491.250, "dur": 0.855, + "args": { + "External id": 1443530,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960496.559, "dur": 11.933, + "args": { + "External id": 1443531,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 8906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960513.577, "dur": 0.844, + "args": { + "External id": 1443532,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960519.581, "dur": 13.138, + "args": { + "External id": 1443533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 8908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960537.634, "dur": 1.612, + "args": { + "External id": 1443534,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960544.131, "dur": 11.389, + "args": { + "External id": 1443535,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 8910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960563.074, "dur": 0.819, + "args": { + "External id": 1443536,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960568.268, "dur": 11.031, + "args": { + "External id": 1443537,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960584.556, "dur": 0.838, + "args": { + "External id": 1443538,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960589.659, "dur": 9.807, + "args": { + "External id": 1443539,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 8914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854960604.519, "dur": 0.875, + "args": { + "External id": 1443540,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413854960610.022, "dur": 10.411, + "args": { + "External id": 1443541,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 8916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854960723.431, "dur": 3089.410, + "args": { + "External id": 1443542,"Record function id": 0, "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413854960747.047, "dur": 1126.876, + "args": { + "External id": 1443543,"Record function id": 0, "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413854960763.264, "dur": 411.897, + "args": { + "External id": 1443544,"Record function id": 0, "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960861.264, "dur": 6.243, + "args": { + "External id": 1443545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 8920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960870.544, "dur": 0.759, + "args": { + "External id": 1443546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960873.205, "dur": 1.148, + "args": { + "External id": 1443547,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960877.134, "dur": 1.183, + "args": { + "External id": 1443548,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960882.195, "dur": 1.390, + "args": { + "External id": 1443549,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960885.165, "dur": 1.307, + "args": { + "External id": 1443550,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 8925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960888.714, "dur": 1.103, + "args": { + "External id": 1443551,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 8926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960891.005, "dur": 1.660, + "args": { + "External id": 1443552,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960896.380, "dur": 2.955, + "args": { + "External id": 1443553,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854960900.668, "dur": 0.893, + "args": { + "External id": 1443554,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 8929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854960920.742, "dur": 218.281, + "args": { + "External id": 1443555,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854960938.200, "dur": 194.770, + "args": { + "External id": 1443556,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 8931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854960957.661, "dur": 13.419, + "args": { + "External id": 1443557,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854960974.877, "dur": 128.453, + "args": { + "External id": 1443558,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 8933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854960998.701, "dur": 104.275, + "args": { + "External id": 1443559,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 8934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961003.238, "dur": 7.076, + "args": { + "External id": 1443560,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854961012.249, "dur": 89.515, + "args": { + "External id": 1443561,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 8936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 2338706, "tid": 2379422, + "ts": 6413854961275.115, "dur": 591.059, + "args": { + "External id": 1443562,"Record function id": 0, "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413854961293.741, "dur": 559.928, + "args": { + "External id": 1443563,"Record function id": 0, "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854961361.093, "dur": 6.366, + "args": { + "External id": 1443564,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854961384.193, "dur": 30.682, + "args": { + "External id": 1443565,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961388.791, "dur": 1.634, + "args": { + "External id": 1443566,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961392.920, "dur": 2.108, + "args": { + "External id": 1443567,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961396.578, "dur": 0.768, + "args": { + "External id": 1443568,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961398.807, "dur": 2.484, + "args": { + "External id": 1443569,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961403.982, "dur": 0.237, + "args": { + "External id": 1443570,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961405.430, "dur": 0.326, + "args": { + "External id": 1443571,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961407.044, "dur": 0.347, + "args": { + "External id": 1443572,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961409.749, "dur": 0.393, + "args": { + "External id": 1443573,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961411.222, "dur": 0.294, + "args": { + "External id": 1443574,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854961426.417, "dur": 39.932, + "args": { + "External id": 1443575,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413854961501.786, "dur": 114.832, + "args": { + "External id": 1443576,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 8951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854961512.423, "dur": 4.407, + "args": { + "External id": 1443577,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413854961522.511, "dur": 10.240, + "args": { + "External id": 1443578,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413854961527.174, "dur": 5.138, + "args": { + "External id": 1443579,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 8954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961530.329, "dur": 0.497, + "args": { + "External id": 1443580,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 8955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413854961538.741, "dur": 32.147, + "args": { + "External id": 1443581,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 8956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961540.736, "dur": 2.672, + "args": { + "External id": 1443582,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961545.069, "dur": 2.171, + "args": { + "External id": 1443583,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961548.564, "dur": 0.570, + "args": { + "External id": 1443584,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961550.609, "dur": 0.374, + "args": { + "External id": 1443585,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961552.938, "dur": 0.332, + "args": { + "External id": 1443586,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961554.729, "dur": 0.362, + "args": { + "External id": 1443587,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961556.449, "dur": 0.327, + "args": { + "External id": 1443588,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961559.304, "dur": 0.369, + "args": { + "External id": 1443589,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854961560.998, "dur": 2.571, + "args": { + "External id": 1443590,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 8965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854961581.708, "dur": 28.026, + "args": { + "External id": 1443591,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 8966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413854961660.691, "dur": 121.476, + "args": { + "External id": 1443592,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 8967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854961694.120, "dur": 84.626, + "args": { + "External id": 1443593,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8968, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413854961703.580, "dur": 71.018, + "args": { + "External id": 1443594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 8969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413854961802.807, "dur": 1.924, + "args": { + "External id": 1443595,"Record function id": 0, "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": 8970, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854961880.956, "dur": 1907.143, + "args": { + "External id": 1443596,"Sequence number": 15348921, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 8971 + } + }, + { + "ph": "f", "id": 414, "pid": 2338706, "tid": 2379422, "ts": 6413854961880.956, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962028.713, "dur": 150.299, + "args": { + "External id": 1443597,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 8972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854962234.078, "dur": 44.711, + "args": { + "External id": 1443598,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 8973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962300.885, "dur": 53.634, + "args": { + "External id": 1443599,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 8974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962365.739, "dur": 32.254, + "args": { + "External id": 1443600,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962405.042, "dur": 33.980, + "args": { + "External id": 1443601,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962446.002, "dur": 27.840, + "args": { + "External id": 1443602,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 8977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962483.726, "dur": 29.866, + "args": { + "External id": 1443603,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 8978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854962539.890, "dur": 26.306, + "args": { + "External id": 1443604,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 8979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413854962586.810, "dur": 32.441, + "args": { + "External id": 1443605,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854962643.755, "dur": 20.861, + "args": { + "External id": 1443606,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 8981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854962678.771, "dur": 17.241, + "args": { + "External id": 1443607,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 8982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962705.353, "dur": 38.725, + "args": { + "External id": 1443608,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 8983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854962747.448, "dur": 35.298, + "args": { + "External id": 1443609,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 8984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413854962813.499, "dur": 332.432, + "args": { + "External id": 1443610,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 8985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854962900.436, "dur": 6.140, + "args": { + "External id": 1443611,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854962908.815, "dur": 3.338, + "args": { + "External id": 1443612,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854962913.647, "dur": 2.689, + "args": { + "External id": 1443613,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854962917.626, "dur": 5.336, + "args": { + "External id": 1443614,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854962973.157, "dur": 23.723, + "args": { + "External id": 1443615,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854962975.791, "dur": 20.500, + "args": { + "External id": 1443616,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854962999.762, "dur": 36.872, + "args": { + "External id": 1443617,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854963005.898, "dur": 1.789, + "args": { + "External id": 1443618,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413854963038.333, "dur": 2.511, + "args": { + "External id": 1443619,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854963039.874, "dur": 0.872, + "args": { + "External id": 1443620,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 8995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413854963042.302, "dur": 52.593, + "args": { + "External id": 1443621,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 8996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854963044.957, "dur": 0.565, + "args": { + "External id": 1443622,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 8997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413854963190.287, "dur": 48.209, + "args": { + "External id": 1443623,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854963266.647, "dur": 21.531, + "args": { + "External id": 1443624,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854963298.035, "dur": 54.552, + "args": { + "External id": 1443625,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854963358.569, "dur": 40.212, + "args": { + "External id": 1443626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854963411.087, "dur": 22.437, + "args": { + "External id": 1443627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854963442.367, "dur": 33.692, + "args": { + "External id": 1443628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854963484.057, "dur": 28.855, + "args": { + "External id": 1443629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413854963520.436, "dur": 31.756, + "args": { + "External id": 1443630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413854963570.672, "dur": 24.677, + "args": { + "External id": 1443631,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854963611.580, "dur": 25.668, + "args": { + "External id": 1443632,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413854963671.005, "dur": 18.655, + "args": { + "External id": 1443633,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413854963705.703, "dur": 14.896, + "args": { + "External id": 1443634,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413854963735.632, "dur": 17.160, + "args": { + "External id": 1443635,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963835.963, "dur": 17.420, + "args": { + "External id": 1443636,"Record function id": 0, "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963839.961, "dur": 12.243, + "args": { + "External id": 1443637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963844.767, "dur": 6.448, + "args": { + "External id": 1443638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963846.972, "dur": 4.121, + "args": { + "External id": 1443639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963857.368, "dur": 6.231, + "args": { + "External id": 1443640,"Record function id": 0, "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963859.204, "dur": 3.891, + "args": { + "External id": 1443641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963859.932, "dur": 2.363, + "args": { + "External id": 1443642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963860.972, "dur": 1.199, + "args": { + "External id": 1443643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963866.961, "dur": 5.682, + "args": { + "External id": 1443644,"Record function id": 0, "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963868.639, "dur": 3.503, + "args": { + "External id": 1443645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963869.256, "dur": 2.313, + "args": { + "External id": 1443646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963870.363, "dur": 1.121, + "args": { + "External id": 1443647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963875.942, "dur": 5.681, + "args": { + "External id": 1443648,"Record function id": 0, "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963877.509, "dur": 3.700, + "args": { + "External id": 1443649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963878.469, "dur": 2.294, + "args": { + "External id": 1443650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963879.662, "dur": 1.019, + "args": { + "External id": 1443651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963884.852, "dur": 5.015, + "args": { + "External id": 1443652,"Record function id": 0, "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963886.222, "dur": 3.197, + "args": { + "External id": 1443653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963886.664, "dur": 2.144, + "args": { + "External id": 1443654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963887.599, "dur": 1.134, + "args": { + "External id": 1443655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963893.035, "dur": 7.580, + "args": { + "External id": 1443656,"Record function id": 0, "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963894.842, "dur": 5.333, + "args": { + "External id": 1443657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963895.292, "dur": 4.318, + "args": { + "External id": 1443658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963896.312, "dur": 3.196, + "args": { + "External id": 1443659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963904.042, "dur": 6.103, + "args": { + "External id": 1443660,"Record function id": 0, "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963905.625, "dur": 4.097, + "args": { + "External id": 1443661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963906.328, "dur": 2.733, + "args": { + "External id": 1443662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963907.641, "dur": 1.347, + "args": { + "External id": 1443663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963913.203, "dur": 5.845, + "args": { + "External id": 1443664,"Record function id": 0, "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963914.807, "dur": 3.829, + "args": { + "External id": 1443665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963915.426, "dur": 2.397, + "args": { + "External id": 1443666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963916.538, "dur": 1.211, + "args": { + "External id": 1443667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963922.829, "dur": 5.237, + "args": { + "External id": 1443668,"Record function id": 0, "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413854963924.343, "dur": 3.306, + "args": { + "External id": 1443669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963924.923, "dur": 2.072, + "args": { + "External id": 1443670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413854963925.947, "dur": 0.967, + "args": { + "External id": 1443671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854963932.969, "dur": 65178.414, + "args": { + "External id": 1443672,"Record function id": 0, "Sequence number": 15348920, "Fwd thread id": 1, "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413854963934.333, "dur": 65165.352, + "args": { + "External id": 1443673,"Sequence number": 15348920, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9048 + } + }, + { + "ph": "f", "id": 415, "pid": 2338706, "tid": 2379422, "ts": 6413854963934.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413854963966.365, "dur": 61.261, + "args": { + "External id": 1443674,"Record function id": 0, "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413854964037.643, "dur": 108.029, + "args": { + "External id": 1443675,"Record function id": 0, "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 2338706, "tid": 2379422, + "ts": 6413854964154.208, "dur": 64935.643, + "args": { + "External id": 1443676,"Record function id": 0, "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854964250.898, "dur": 7.654, + "args": { + "External id": 1443677,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413854964269.457, "dur": 5.353, + "args": { + "External id": 1443678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854964289.495, "dur": 63829.202, + "args": { + "External id": 1443679,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413854964303.825, "dur": 63801.064, + "args": { + "External id": 1443680,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413854964533.261, "dur": 19.281, + "args": { + "External id": 1443681,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413854964578.637, "dur": 63452.913, + "args": { + "External id": 1443682,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413854964581.730, "dur": 63448.707, + "args": { + "External id": 1443683,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413854964586.429, "dur": 10.761, + "args": { + "External id": 1443684,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413854964601.593, "dur": 63423.713, + "args": { + "External id": 1443685,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855028236.288, "dur": 13.479, + "args": { + "External id": 1443686,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855028240.096, "dur": 9.324, + "args": { + "External id": 1443687,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028281.328, "dur": 378.679, + "args": { + "External id": 1443688,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855028315.547, "dur": 339.333, + "args": { + "External id": 1443689,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9064, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855028327.731, "dur": 320.941, + "args": { + "External id": 1443690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855028680.744, "dur": 2.149, + "args": { + "External id": 1443691,"Record function id": 0, "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": 9066, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028741.344, "dur": 6.875, + "args": { + "External id": 1443692,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028760.379, "dur": 34.095, + "args": { + "External id": 1443693,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028805.207, "dur": 3.392, + "args": { + "External id": 1443694,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028814.677, "dur": 11.803, + "args": { + "External id": 1443695,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028831.849, "dur": 1.064, + "args": { + "External id": 1443696,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028838.692, "dur": 11.935, + "args": { + "External id": 1443697,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028855.712, "dur": 0.653, + "args": { + "External id": 1443698,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028861.414, "dur": 10.716, + "args": { + "External id": 1443699,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028876.467, "dur": 1.037, + "args": { + "External id": 1443700,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028883.101, "dur": 11.080, + "args": { + "External id": 1443701,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028898.365, "dur": 1.084, + "args": { + "External id": 1443702,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028903.599, "dur": 10.442, + "args": { + "External id": 1443703,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028918.201, "dur": 0.693, + "args": { + "External id": 1443704,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028923.492, "dur": 9.978, + "args": { + "External id": 1443705,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028937.461, "dur": 1.062, + "args": { + "External id": 1443706,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028942.567, "dur": 10.728, + "args": { + "External id": 1443707,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855028960.135, "dur": 1.062, + "args": { + "External id": 1443708,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855028965.924, "dur": 10.472, + "args": { + "External id": 1443709,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855029129.257, "dur": 3120.222, + "args": { + "External id": 1443710,"Record function id": 0, "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413855029153.119, "dur": 1151.572, + "args": { + "External id": 1443711,"Record function id": 0, "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413855029170.530, "dur": 334.747, + "args": { + "External id": 1443712,"Record function id": 0, "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029264.945, "dur": 6.641, + "args": { + "External id": 1443713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029274.695, "dur": 1.009, + "args": { + "External id": 1443714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029277.881, "dur": 1.038, + "args": { + "External id": 1443715,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029280.755, "dur": 0.929, + "args": { + "External id": 1443716,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029283.917, "dur": 0.940, + "args": { + "External id": 1443717,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029286.148, "dur": 1.007, + "args": { + "External id": 1443718,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029288.815, "dur": 0.832, + "args": { + "External id": 1443719,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029291.468, "dur": 1.914, + "args": { + "External id": 1443720,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029296.790, "dur": 2.393, + "args": { + "External id": 1443721,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855029300.652, "dur": 0.748, + "args": { + "External id": 1443722,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855029319.344, "dur": 155.548, + "args": { + "External id": 1443723,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855029336.995, "dur": 133.371, + "args": { + "External id": 1443724,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855029354.350, "dur": 14.129, + "args": { + "External id": 1443725,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855029372.524, "dur": 68.264, + "args": { + "External id": 1443726,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855029375.542, "dur": 64.936, + "args": { + "External id": 1443727,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029380.121, "dur": 5.546, + "args": { + "External id": 1443728,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855029387.892, "dur": 51.907, + "args": { + "External id": 1443729,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9104 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 2338706, "tid": 2379422, + "ts": 6413855029595.540, "dur": 701.322, + "args": { + "External id": 1443730,"Record function id": 0, "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413855029612.454, "dur": 670.998, + "args": { + "External id": 1443731,"Record function id": 0, "Ev Idx": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855029678.269, "dur": 4.934, + "args": { + "External id": 1443732,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855029699.147, "dur": 31.165, + "args": { + "External id": 1443733,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029704.660, "dur": 2.217, + "args": { + "External id": 1443734,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029709.563, "dur": 0.566, + "args": { + "External id": 1443735,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029711.833, "dur": 0.788, + "args": { + "External id": 1443736,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029714.010, "dur": 2.319, + "args": { + "External id": 1443737,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029718.443, "dur": 0.521, + "args": { + "External id": 1443738,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029720.985, "dur": 0.403, + "args": { + "External id": 1443739,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029722.558, "dur": 0.468, + "args": { + "External id": 1443740,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029725.068, "dur": 0.353, + "args": { + "External id": 1443741,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029726.892, "dur": 0.569, + "args": { + "External id": 1443742,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855029741.645, "dur": 40.715, + "args": { + "External id": 1443743,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855029810.650, "dur": 185.444, + "args": { + "External id": 1443744,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855029820.929, "dur": 2.729, + "args": { + "External id": 1443745,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855029828.978, "dur": 10.784, + "args": { + "External id": 1443746,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855029833.876, "dur": 5.461, + "args": { + "External id": 1443747,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029837.766, "dur": 0.496, + "args": { + "External id": 1443748,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855029845.762, "dur": 81.231, + "args": { + "External id": 1443749,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029901.749, "dur": 2.591, + "args": { + "External id": 1443750,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029906.617, "dur": 0.453, + "args": { + "External id": 1443751,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029909.158, "dur": 0.391, + "args": { + "External id": 1443752,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029911.348, "dur": 0.262, + "args": { + "External id": 1443753,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029912.615, "dur": 0.535, + "args": { + "External id": 1443754,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029914.761, "dur": 0.464, + "args": { + "External id": 1443755,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029916.528, "dur": 0.270, + "args": { + "External id": 1443756,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029918.115, "dur": 0.457, + "args": { + "External id": 1443757,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855029920.236, "dur": 2.724, + "args": { + "External id": 1443758,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855029937.878, "dur": 32.431, + "args": { + "External id": 1443759,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855030047.298, "dur": 159.251, + "args": { + "External id": 1443760,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855030108.941, "dur": 93.597, + "args": { + "External id": 1443761,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9136, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855030120.078, "dur": 76.794, + "args": { + "External id": 1443762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855030224.749, "dur": 2.000, + "args": { + "External id": 1443763,"Record function id": 0, "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": 9138, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855030312.580, "dur": 1911.311, + "args": { + "External id": 1443764,"Sequence number": 15348919, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9139 + } + }, + { + "ph": "f", "id": 416, "pid": 2338706, "tid": 2379422, "ts": 6413855030312.580, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855030429.461, "dur": 107.039, + "args": { + "External id": 1443765,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855030579.544, "dur": 41.035, + "args": { + "External id": 1443766,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855030641.136, "dur": 50.154, + "args": { + "External id": 1443767,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855030700.945, "dur": 30.755, + "args": { + "External id": 1443768,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855030738.170, "dur": 32.413, + "args": { + "External id": 1443769,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855030777.356, "dur": 26.866, + "args": { + "External id": 1443770,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855030813.270, "dur": 29.035, + "args": { + "External id": 1443771,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855030866.879, "dur": 22.977, + "args": { + "External id": 1443772,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855030912.112, "dur": 28.901, + "args": { + "External id": 1443773,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855030963.074, "dur": 38.336, + "args": { + "External id": 1443774,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855031020.204, "dur": 17.731, + "args": { + "External id": 1443775,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031049.648, "dur": 79.511, + "args": { + "External id": 1443776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031135.601, "dur": 33.509, + "args": { + "External id": 1443777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855031201.434, "dur": 266.322, + "args": { + "External id": 1443778,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855031286.080, "dur": 6.522, + "args": { + "External id": 1443779,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855031297.897, "dur": 3.501, + "args": { + "External id": 1443780,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855031303.177, "dur": 2.652, + "args": { + "External id": 1443781,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855031306.989, "dur": 4.673, + "args": { + "External id": 1443782,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855031360.735, "dur": 5.441, + "args": { + "External id": 1443783,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855031362.875, "dur": 3.151, + "args": { + "External id": 1443784,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855031368.402, "dur": 34.067, + "args": { + "External id": 1443785,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855031374.256, "dur": 1.836, + "args": { + "External id": 1443786,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855031404.309, "dur": 1.854, + "args": { + "External id": 1443787,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855031405.273, "dur": 0.783, + "args": { + "External id": 1443788,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855031407.301, "dur": 17.369, + "args": { + "External id": 1443789,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855031409.975, "dur": 0.571, + "args": { + "External id": 1443790,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855031505.957, "dur": 31.389, + "args": { + "External id": 1443791,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855031554.439, "dur": 18.747, + "args": { + "External id": 1443792,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031581.413, "dur": 42.673, + "args": { + "External id": 1443793,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031631.505, "dur": 40.486, + "args": { + "External id": 1443794,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031680.542, "dur": 36.200, + "args": { + "External id": 1443795,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031732.816, "dur": 41.384, + "args": { + "External id": 1443796,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031782.486, "dur": 31.346, + "args": { + "External id": 1443797,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855031876.227, "dur": 47.533, + "args": { + "External id": 1443798,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855031951.642, "dur": 40.372, + "args": { + "External id": 1443799,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855032013.898, "dur": 28.732, + "args": { + "External id": 1443800,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855032102.099, "dur": 21.821, + "args": { + "External id": 1443801,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855032143.236, "dur": 15.166, + "args": { + "External id": 1443802,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855032172.119, "dur": 17.339, + "args": { + "External id": 1443803,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032272.273, "dur": 17.262, + "args": { + "External id": 1443804,"Record function id": 0, "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032276.227, "dur": 12.306, + "args": { + "External id": 1443805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032280.749, "dur": 6.866, + "args": { + "External id": 1443806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032283.009, "dur": 4.498, + "args": { + "External id": 1443807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032293.350, "dur": 6.939, + "args": { + "External id": 1443808,"Record function id": 0, "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032295.641, "dur": 4.161, + "args": { + "External id": 1443809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032296.401, "dur": 2.917, + "args": { + "External id": 1443810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032297.701, "dur": 1.493, + "args": { + "External id": 1443811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032303.797, "dur": 5.021, + "args": { + "External id": 1443812,"Record function id": 0, "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032305.009, "dur": 3.369, + "args": { + "External id": 1443813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032305.611, "dur": 2.304, + "args": { + "External id": 1443814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032306.676, "dur": 1.109, + "args": { + "External id": 1443815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032311.939, "dur": 5.239, + "args": { + "External id": 1443816,"Record function id": 0, "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032313.173, "dur": 3.590, + "args": { + "External id": 1443817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032313.676, "dur": 2.472, + "args": { + "External id": 1443818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032314.543, "dur": 1.523, + "args": { + "External id": 1443819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032320.213, "dur": 4.835, + "args": { + "External id": 1443820,"Record function id": 0, "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032321.382, "dur": 3.236, + "args": { + "External id": 1443821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032321.851, "dur": 2.206, + "args": { + "External id": 1443822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032322.752, "dur": 1.231, + "args": { + "External id": 1443823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032328.098, "dur": 7.226, + "args": { + "External id": 1443824,"Record function id": 0, "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032329.663, "dur": 5.248, + "args": { + "External id": 1443825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032330.188, "dur": 4.032, + "args": { + "External id": 1443826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032331.003, "dur": 3.140, + "args": { + "External id": 1443827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032338.496, "dur": 5.494, + "args": { + "External id": 1443828,"Record function id": 0, "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032340.107, "dur": 3.491, + "args": { + "External id": 1443829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032341.045, "dur": 2.139, + "args": { + "External id": 1443830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032342.065, "dur": 1.026, + "args": { + "External id": 1443831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032347.507, "dur": 4.260, + "args": { + "External id": 1443832,"Record function id": 0, "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032348.833, "dur": 2.500, + "args": { + "External id": 1443833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032349.352, "dur": 1.568, + "args": { + "External id": 1443834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032349.898, "dur": 0.940, + "args": { + "External id": 1443835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032355.397, "dur": 4.687, + "args": { + "External id": 1443836,"Record function id": 0, "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855032356.510, "dur": 3.156, + "args": { + "External id": 1443837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032357.007, "dur": 1.948, + "args": { + "External id": 1443838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855032357.927, "dur": 0.943, + "args": { + "External id": 1443839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855032364.724, "dur": 66091.309, + "args": { + "External id": 1443840,"Record function id": 0, "Sequence number": 15348918, "Fwd thread id": 1, "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855032426.100, "dur": 66020.593, + "args": { + "External id": 1443841,"Sequence number": 15348918, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9216 + } + }, + { + "ph": "f", "id": 417, "pid": 2338706, "tid": 2379422, "ts": 6413855032426.100, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413855032460.003, "dur": 43.689, + "args": { + "External id": 1443842,"Record function id": 0, "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413855032512.059, "dur": 67.464, + "args": { + "External id": 1443843,"Record function id": 0, "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 2338706, "tid": 2379422, + "ts": 6413855032585.913, "dur": 65852.566, + "args": { + "External id": 1443844,"Record function id": 0, "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855032678.861, "dur": 7.556, + "args": { + "External id": 1443845,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855032696.183, "dur": 4.882, + "args": { + "External id": 1443846,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855032716.188, "dur": 64709.667, + "args": { + "External id": 1443847,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855032730.335, "dur": 64682.141, + "args": { + "External id": 1443848,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855032925.450, "dur": 18.852, + "args": { + "External id": 1443849,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855032968.660, "dur": 64396.629, + "args": { + "External id": 1443850,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855032971.590, "dur": 64392.632, + "args": { + "External id": 1443851,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855032976.117, "dur": 31.760, + "args": { + "External id": 1443852,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855033013.552, "dur": 64345.875, + "args": { + "External id": 1443853,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855097536.748, "dur": 12.522, + "args": { + "External id": 1443854,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855097540.528, "dur": 8.377, + "args": { + "External id": 1443855,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855097580.555, "dur": 435.174, + "args": { + "External id": 1443856,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855097614.920, "dur": 395.097, + "args": { + "External id": 1443857,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9232, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855097626.889, "dur": 376.652, + "args": { + "External id": 1443858,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855098039.241, "dur": 2.566, + "args": { + "External id": 1443859,"Record function id": 0, "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": 9234, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098139.659, "dur": 7.528, + "args": { + "External id": 1443860,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098160.444, "dur": 38.317, + "args": { + "External id": 1443861,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098208.464, "dur": 3.612, + "args": { + "External id": 1443862,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098218.496, "dur": 11.175, + "args": { + "External id": 1443863,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098234.769, "dur": 0.972, + "args": { + "External id": 1443864,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098240.791, "dur": 10.587, + "args": { + "External id": 1443865,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098256.182, "dur": 0.857, + "args": { + "External id": 1443866,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098261.358, "dur": 11.569, + "args": { + "External id": 1443867,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098276.850, "dur": 0.941, + "args": { + "External id": 1443868,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098282.165, "dur": 12.009, + "args": { + "External id": 1443869,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098298.406, "dur": 0.991, + "args": { + "External id": 1443870,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098303.708, "dur": 11.020, + "args": { + "External id": 1443871,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098318.999, "dur": 0.862, + "args": { + "External id": 1443872,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098323.827, "dur": 12.409, + "args": { + "External id": 1443873,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098342.872, "dur": 0.763, + "args": { + "External id": 1443874,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098348.039, "dur": 10.940, + "args": { + "External id": 1443875,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098362.795, "dur": 0.886, + "args": { + "External id": 1443876,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098367.660, "dur": 12.884, + "args": { + "External id": 1443877,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855098471.878, "dur": 3029.017, + "args": { + "External id": 1443878,"Record function id": 0, "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413855098492.966, "dur": 1102.778, + "args": { + "External id": 1443879,"Record function id": 0, "Ev Idx": 9254 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413855098509.319, "dur": 315.109, + "args": { + "External id": 1443880,"Record function id": 0, "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098594.846, "dur": 6.155, + "args": { + "External id": 1443881,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098604.443, "dur": 0.856, + "args": { + "External id": 1443882,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098606.895, "dur": 0.774, + "args": { + "External id": 1443883,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098609.605, "dur": 0.728, + "args": { + "External id": 1443884,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098611.978, "dur": 0.877, + "args": { + "External id": 1443885,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098616.376, "dur": 0.918, + "args": { + "External id": 1443886,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098619.018, "dur": 0.717, + "args": { + "External id": 1443887,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098621.068, "dur": 1.867, + "args": { + "External id": 1443888,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098624.258, "dur": 2.758, + "args": { + "External id": 1443889,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855098630.061, "dur": 0.540, + "args": { + "External id": 1443890,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855098647.958, "dur": 146.688, + "args": { + "External id": 1443891,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855098664.761, "dur": 125.254, + "args": { + "External id": 1443892,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855098681.211, "dur": 13.938, + "args": { + "External id": 1443893,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855098699.242, "dur": 63.494, + "args": { + "External id": 1443894,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855098702.155, "dur": 60.222, + "args": { + "External id": 1443895,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855098706.024, "dur": 5.476, + "args": { + "External id": 1443896,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855098713.396, "dur": 48.317, + "args": { + "External id": 1443897,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9272 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 2338706, "tid": 2379422, + "ts": 6413855098917.128, "dur": 670.869, + "args": { + "External id": 1443898,"Record function id": 0, "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413855098932.899, "dur": 641.931, + "args": { + "External id": 1443899,"Record function id": 0, "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855099017.937, "dur": 6.868, + "args": { + "External id": 1443900,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855099043.811, "dur": 80.660, + "args": { + "External id": 1443901,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099049.911, "dur": 1.774, + "args": { + "External id": 1443902,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099101.547, "dur": 0.835, + "args": { + "External id": 1443903,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099104.798, "dur": 0.808, + "args": { + "External id": 1443904,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099107.262, "dur": 2.600, + "args": { + "External id": 1443905,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099110.921, "dur": 0.530, + "args": { + "External id": 1443906,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099113.379, "dur": 0.392, + "args": { + "External id": 1443907,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099115.569, "dur": 0.364, + "args": { + "External id": 1443908,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099116.842, "dur": 0.507, + "args": { + "External id": 1443909,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099119.142, "dur": 0.431, + "args": { + "External id": 1443910,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855099137.978, "dur": 49.697, + "args": { + "External id": 1443911,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855099224.507, "dur": 113.870, + "args": { + "External id": 1443912,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855099236.762, "dur": 4.536, + "args": { + "External id": 1443913,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855099246.791, "dur": 10.913, + "args": { + "External id": 1443914,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855099251.632, "dur": 5.629, + "args": { + "External id": 1443915,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099255.482, "dur": 0.707, + "args": { + "External id": 1443916,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855099264.441, "dur": 25.731, + "args": { + "External id": 1443917,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099266.644, "dur": 2.863, + "args": { + "External id": 1443918,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099270.934, "dur": 0.509, + "args": { + "External id": 1443919,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099273.108, "dur": 0.474, + "args": { + "External id": 1443920,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099274.934, "dur": 0.375, + "args": { + "External id": 1443921,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099276.678, "dur": 0.358, + "args": { + "External id": 1443922,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099278.534, "dur": 0.427, + "args": { + "External id": 1443923,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099280.858, "dur": 0.656, + "args": { + "External id": 1443924,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099282.827, "dur": 0.402, + "args": { + "External id": 1443925,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855099284.999, "dur": 2.756, + "args": { + "External id": 1443926,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855099300.046, "dur": 30.252, + "args": { + "External id": 1443927,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855099387.328, "dur": 118.177, + "args": { + "External id": 1443928,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855099412.710, "dur": 89.141, + "args": { + "External id": 1443929,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9304, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855099422.909, "dur": 74.256, + "args": { + "External id": 1443930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855099521.056, "dur": 1.777, + "args": { + "External id": 1443931,"Record function id": 0, "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": 9306, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855099604.131, "dur": 1871.732, + "args": { + "External id": 1443932,"Sequence number": 15348917, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9307 + } + }, + { + "ph": "f", "id": 418, "pid": 2338706, "tid": 2379422, "ts": 6413855099604.131, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855099718.511, "dur": 104.180, + "args": { + "External id": 1443933,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855099860.662, "dur": 40.807, + "args": { + "External id": 1443934,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855099923.059, "dur": 48.620, + "args": { + "External id": 1443935,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100003.961, "dur": 36.954, + "args": { + "External id": 1443936,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100048.501, "dur": 73.637, + "args": { + "External id": 1443937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100132.603, "dur": 29.161, + "args": { + "External id": 1443938,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100170.702, "dur": 28.972, + "args": { + "External id": 1443939,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855100229.279, "dur": 27.283, + "args": { + "External id": 1443940,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855100277.152, "dur": 31.836, + "args": { + "External id": 1443941,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855100330.243, "dur": 19.527, + "args": { + "External id": 1443942,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855100367.604, "dur": 15.373, + "args": { + "External id": 1443943,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100393.519, "dur": 37.327, + "args": { + "External id": 1443944,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100434.354, "dur": 34.497, + "args": { + "External id": 1443945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855100498.007, "dur": 253.616, + "args": { + "External id": 1443946,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855100581.107, "dur": 6.309, + "args": { + "External id": 1443947,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855100589.591, "dur": 3.515, + "args": { + "External id": 1443948,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855100594.536, "dur": 2.540, + "args": { + "External id": 1443949,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855100598.579, "dur": 4.507, + "args": { + "External id": 1443950,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855100650.958, "dur": 4.968, + "args": { + "External id": 1443951,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855100652.765, "dur": 2.984, + "args": { + "External id": 1443952,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855100657.626, "dur": 31.289, + "args": { + "External id": 1443953,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855100662.844, "dur": 1.635, + "args": { + "External id": 1443954,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855100690.553, "dur": 1.885, + "args": { + "External id": 1443955,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855100691.591, "dur": 0.750, + "args": { + "External id": 1443956,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855100693.767, "dur": 14.396, + "args": { + "External id": 1443957,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855100696.298, "dur": 0.562, + "args": { + "External id": 1443958,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855100786.526, "dur": 29.413, + "args": { + "External id": 1443959,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855100833.892, "dur": 17.836, + "args": { + "External id": 1443960,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100860.260, "dur": 40.808, + "args": { + "External id": 1443961,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855100909.399, "dur": 37.801, + "args": { + "External id": 1443962,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855101005.902, "dur": 44.907, + "args": { + "External id": 1443963,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855101104.436, "dur": 40.908, + "args": { + "External id": 1443964,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855101158.804, "dur": 28.454, + "args": { + "External id": 1443965,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855101195.112, "dur": 34.041, + "args": { + "External id": 1443966,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855101254.876, "dur": 31.150, + "args": { + "External id": 1443967,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855101305.380, "dur": 28.856, + "args": { + "External id": 1443968,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855101350.529, "dur": 20.290, + "args": { + "External id": 1443969,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855101391.577, "dur": 16.806, + "args": { + "External id": 1443970,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855101423.374, "dur": 18.506, + "args": { + "External id": 1443971,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101523.485, "dur": 17.069, + "args": { + "External id": 1443972,"Record function id": 0, "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101527.584, "dur": 11.964, + "args": { + "External id": 1443973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101532.163, "dur": 6.252, + "args": { + "External id": 1443974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101533.869, "dur": 4.423, + "args": { + "External id": 1443975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101544.701, "dur": 6.877, + "args": { + "External id": 1443976,"Record function id": 0, "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101546.723, "dur": 4.207, + "args": { + "External id": 1443977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101547.588, "dur": 2.801, + "args": { + "External id": 1443978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101548.909, "dur": 1.376, + "args": { + "External id": 1443979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101554.811, "dur": 5.318, + "args": { + "External id": 1443980,"Record function id": 0, "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101556.508, "dur": 3.183, + "args": { + "External id": 1443981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101557.038, "dur": 2.221, + "args": { + "External id": 1443982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101557.979, "dur": 1.182, + "args": { + "External id": 1443983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101563.301, "dur": 7.380, + "args": { + "External id": 1443984,"Record function id": 0, "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101564.575, "dur": 5.633, + "args": { + "External id": 1443985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101565.089, "dur": 4.661, + "args": { + "External id": 1443986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101566.295, "dur": 3.364, + "args": { + "External id": 1443987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101573.832, "dur": 5.342, + "args": { + "External id": 1443988,"Record function id": 0, "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101575.348, "dur": 3.383, + "args": { + "External id": 1443989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101575.971, "dur": 2.305, + "args": { + "External id": 1443990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101576.990, "dur": 1.213, + "args": { + "External id": 1443991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101582.275, "dur": 5.813, + "args": { + "External id": 1443992,"Record function id": 0, "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101584.095, "dur": 3.538, + "args": { + "External id": 1443993,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101584.743, "dur": 2.345, + "args": { + "External id": 1443994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101585.670, "dur": 1.334, + "args": { + "External id": 1443995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101591.450, "dur": 5.195, + "args": { + "External id": 1443996,"Record function id": 0, "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101592.961, "dur": 3.280, + "args": { + "External id": 1443997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101593.405, "dur": 2.393, + "args": { + "External id": 1443998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101594.423, "dur": 1.305, + "args": { + "External id": 1443999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101599.771, "dur": 5.749, + "args": { + "External id": 1444000,"Record function id": 0, "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101601.316, "dur": 3.789, + "args": { + "External id": 1444001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101601.932, "dur": 2.470, + "args": { + "External id": 1444002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101603.003, "dur": 1.318, + "args": { + "External id": 1444003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101608.595, "dur": 4.953, + "args": { + "External id": 1444004,"Record function id": 0, "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855101610.111, "dur": 3.018, + "args": { + "External id": 1444005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101610.589, "dur": 2.087, + "args": { + "External id": 1444006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855101611.435, "dur": 1.158, + "args": { + "External id": 1444007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855101618.005, "dur": 65263.947, + "args": { + "External id": 1444008,"Record function id": 0, "Sequence number": 15348916, "Fwd thread id": 1, "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855101619.400, "dur": 65253.619, + "args": { + "External id": 1444009,"Sequence number": 15348916, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9384 + } + }, + { + "ph": "f", "id": 419, "pid": 2338706, "tid": 2379422, "ts": 6413855101619.400, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413855101649.039, "dur": 42.482, + "args": { + "External id": 1444010,"Record function id": 0, "Ev Idx": 9385 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413855101700.213, "dur": 71.713, + "args": { + "External id": 1444011,"Record function id": 0, "Ev Idx": 9386 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 2338706, "tid": 2379422, + "ts": 6413855101778.124, "dur": 65087.499, + "args": { + "External id": 1444012,"Record function id": 0, "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855101868.952, "dur": 6.781, + "args": { + "External id": 1444013,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855101885.970, "dur": 4.607, + "args": { + "External id": 1444014,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855101909.324, "dur": 63981.553, + "args": { + "External id": 1444015,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855101923.597, "dur": 63953.223, + "args": { + "External id": 1444016,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855102119.118, "dur": 24.175, + "args": { + "External id": 1444017,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855102164.647, "dur": 63666.186, + "args": { + "External id": 1444018,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855102168.077, "dur": 63661.725, + "args": { + "External id": 1444019,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855102172.443, "dur": 13.323, + "args": { + "External id": 1444020,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855102193.276, "dur": 63631.919, + "args": { + "External id": 1444021,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855166018.895, "dur": 12.835, + "args": { + "External id": 1444022,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855166022.563, "dur": 8.562, + "args": { + "External id": 1444023,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166093.918, "dur": 380.154, + "args": { + "External id": 1444024,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855166127.436, "dur": 341.757, + "args": { + "External id": 1444025,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9400, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855166140.577, "dur": 323.429, + "args": { + "External id": 1444026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855166495.372, "dur": 2.295, + "args": { + "External id": 1444027,"Record function id": 0, "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": 9402, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166560.896, "dur": 7.139, + "args": { + "External id": 1444028,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166580.899, "dur": 37.378, + "args": { + "External id": 1444029,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166629.002, "dur": 1.852, + "args": { + "External id": 1444030,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166636.452, "dur": 12.970, + "args": { + "External id": 1444031,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166654.678, "dur": 0.941, + "args": { + "External id": 1444032,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166660.329, "dur": 13.281, + "args": { + "External id": 1444033,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166678.496, "dur": 0.932, + "args": { + "External id": 1444034,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166683.928, "dur": 11.431, + "args": { + "External id": 1444035,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166699.543, "dur": 0.945, + "args": { + "External id": 1444036,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166705.148, "dur": 12.464, + "args": { + "External id": 1444037,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166721.900, "dur": 0.999, + "args": { + "External id": 1444038,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166727.095, "dur": 11.613, + "args": { + "External id": 1444039,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166742.781, "dur": 3.351, + "args": { + "External id": 1444040,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166750.418, "dur": 12.558, + "args": { + "External id": 1444041,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166767.299, "dur": 0.936, + "args": { + "External id": 1444042,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166773.041, "dur": 11.800, + "args": { + "External id": 1444043,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855166789.047, "dur": 0.936, + "args": { + "External id": 1444044,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855166794.001, "dur": 12.144, + "args": { + "External id": 1444045,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855166896.663, "dur": 2972.553, + "args": { + "External id": 1444046,"Record function id": 0, "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413855166918.363, "dur": 1126.864, + "args": { + "External id": 1444047,"Record function id": 0, "Ev Idx": 9422 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413855166934.703, "dur": 393.009, + "args": { + "External id": 1444048,"Record function id": 0, "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167043.947, "dur": 4.757, + "args": { + "External id": 1444049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167052.435, "dur": 33.225, + "args": { + "External id": 1444050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167090.697, "dur": 1.143, + "args": { + "External id": 1444051,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167093.607, "dur": 0.970, + "args": { + "External id": 1444052,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167096.530, "dur": 1.001, + "args": { + "External id": 1444053,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167098.925, "dur": 2.810, + "args": { + "External id": 1444054,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167105.331, "dur": 1.040, + "args": { + "External id": 1444055,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167108.759, "dur": 1.869, + "args": { + "External id": 1444056,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167111.911, "dur": 0.739, + "args": { + "External id": 1444057,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855167114.129, "dur": 0.555, + "args": { + "External id": 1444058,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855167136.474, "dur": 158.046, + "args": { + "External id": 1444059,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855167154.875, "dur": 135.211, + "args": { + "External id": 1444060,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855167172.415, "dur": 15.882, + "args": { + "External id": 1444061,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855167192.152, "dur": 67.654, + "args": { + "External id": 1444062,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855167195.159, "dur": 64.287, + "args": { + "External id": 1444063,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167199.455, "dur": 5.486, + "args": { + "External id": 1444064,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855167206.803, "dur": 52.003, + "args": { + "External id": 1444065,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 2338706, "tid": 2379422, + "ts": 6413855167423.277, "dur": 614.463, + "args": { + "External id": 1444066,"Record function id": 0, "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413855167441.645, "dur": 582.301, + "args": { + "External id": 1444067,"Record function id": 0, "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855167507.885, "dur": 5.132, + "args": { + "External id": 1444068,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855167528.262, "dur": 31.638, + "args": { + "External id": 1444069,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167533.624, "dur": 3.549, + "args": { + "External id": 1444070,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167539.020, "dur": 0.429, + "args": { + "External id": 1444071,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167541.682, "dur": 0.364, + "args": { + "External id": 1444072,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167543.649, "dur": 0.717, + "args": { + "External id": 1444073,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167545.352, "dur": 0.361, + "args": { + "External id": 1444074,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167547.395, "dur": 0.661, + "args": { + "External id": 1444075,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167550.054, "dur": 0.507, + "args": { + "External id": 1444076,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167551.545, "dur": 0.464, + "args": { + "External id": 1444077,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167553.749, "dur": 2.555, + "args": { + "External id": 1444078,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855167570.348, "dur": 41.875, + "args": { + "External id": 1444079,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855167642.190, "dur": 132.243, + "args": { + "External id": 1444080,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855167652.070, "dur": 3.321, + "args": { + "External id": 1444081,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855167660.367, "dur": 10.149, + "args": { + "External id": 1444082,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855167664.839, "dur": 5.244, + "args": { + "External id": 1444083,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167668.061, "dur": 0.725, + "args": { + "External id": 1444084,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855167676.992, "dur": 48.099, + "args": { + "External id": 1444085,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167679.730, "dur": 0.466, + "args": { + "External id": 1444086,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167681.589, "dur": 0.454, + "args": { + "External id": 1444087,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167683.700, "dur": 0.422, + "args": { + "External id": 1444088,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167685.641, "dur": 0.851, + "args": { + "External id": 1444089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167687.430, "dur": 0.383, + "args": { + "External id": 1444090,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167713.438, "dur": 2.630, + "args": { + "External id": 1444091,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167717.826, "dur": 0.530, + "args": { + "External id": 1444092,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167720.313, "dur": 0.557, + "args": { + "External id": 1444093,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855167722.011, "dur": 0.395, + "args": { + "External id": 1444094,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855167736.085, "dur": 31.026, + "args": { + "External id": 1444095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855167819.105, "dur": 115.052, + "args": { + "External id": 1444096,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855167846.601, "dur": 84.316, + "args": { + "External id": 1444097,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9472, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855167856.558, "dur": 70.040, + "args": { + "External id": 1444098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855167950.447, "dur": 1.916, + "args": { + "External id": 1444099,"Record function id": 0, "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": 9474, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855168089.451, "dur": 1754.433, + "args": { + "External id": 1444100,"Sequence number": 15348915, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9475 + } + }, + { + "ph": "f", "id": 420, "pid": 2338706, "tid": 2379422, "ts": 6413855168089.451, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168212.322, "dur": 111.470, + "args": { + "External id": 1444101,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855168372.105, "dur": 41.752, + "args": { + "External id": 1444102,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168431.317, "dur": 49.421, + "args": { + "External id": 1444103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168490.494, "dur": 30.827, + "args": { + "External id": 1444104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168527.687, "dur": 33.604, + "args": { + "External id": 1444105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168570.129, "dur": 27.502, + "args": { + "External id": 1444106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168604.114, "dur": 28.729, + "args": { + "External id": 1444107,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855168658.768, "dur": 23.059, + "args": { + "External id": 1444108,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855168702.196, "dur": 28.662, + "args": { + "External id": 1444109,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855168753.606, "dur": 19.748, + "args": { + "External id": 1444110,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855168788.436, "dur": 14.688, + "args": { + "External id": 1444111,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168812.476, "dur": 35.530, + "args": { + "External id": 1444112,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855168851.907, "dur": 33.643, + "args": { + "External id": 1444113,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855168914.306, "dur": 320.104, + "args": { + "External id": 1444114,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855169016.290, "dur": 9.418, + "args": { + "External id": 1444115,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855169028.042, "dur": 2.609, + "args": { + "External id": 1444116,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855169032.063, "dur": 2.257, + "args": { + "External id": 1444117,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855169035.730, "dur": 2.591, + "args": { + "External id": 1444118,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855169120.826, "dur": 5.383, + "args": { + "External id": 1444119,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855169122.888, "dur": 3.044, + "args": { + "External id": 1444120,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855169128.042, "dur": 32.004, + "args": { + "External id": 1444121,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855169133.872, "dur": 1.627, + "args": { + "External id": 1444122,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855169161.716, "dur": 1.729, + "args": { + "External id": 1444123,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855169162.563, "dur": 0.797, + "args": { + "External id": 1444124,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855169164.640, "dur": 15.054, + "args": { + "External id": 1444125,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855169166.724, "dur": 0.699, + "args": { + "External id": 1444126,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855169272.403, "dur": 26.876, + "args": { + "External id": 1444127,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855169323.612, "dur": 18.027, + "args": { + "External id": 1444128,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855169350.606, "dur": 48.293, + "args": { + "External id": 1444129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855169406.659, "dur": 40.221, + "args": { + "External id": 1444130,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855169458.049, "dur": 35.537, + "args": { + "External id": 1444131,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855169507.818, "dur": 38.422, + "args": { + "External id": 1444132,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855169554.362, "dur": 30.402, + "args": { + "External id": 1444133,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855169591.527, "dur": 33.618, + "args": { + "External id": 1444134,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855169645.134, "dur": 28.267, + "args": { + "External id": 1444135,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855169689.280, "dur": 25.354, + "args": { + "External id": 1444136,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855169731.550, "dur": 18.219, + "args": { + "External id": 1444137,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855169763.402, "dur": 13.691, + "args": { + "External id": 1444138,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855169792.878, "dur": 18.251, + "args": { + "External id": 1444139,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169891.703, "dur": 16.362, + "args": { + "External id": 1444140,"Record function id": 0, "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169895.522, "dur": 11.701, + "args": { + "External id": 1444141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169900.013, "dur": 6.157, + "args": { + "External id": 1444142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169902.075, "dur": 3.989, + "args": { + "External id": 1444143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169911.840, "dur": 6.108, + "args": { + "External id": 1444144,"Record function id": 0, "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169913.315, "dur": 4.106, + "args": { + "External id": 1444145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169914.107, "dur": 2.757, + "args": { + "External id": 1444146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169915.266, "dur": 1.461, + "args": { + "External id": 1444147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169921.137, "dur": 5.586, + "args": { + "External id": 1444148,"Record function id": 0, "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169922.603, "dur": 3.613, + "args": { + "External id": 1444149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169923.266, "dur": 2.445, + "args": { + "External id": 1444150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169924.438, "dur": 1.192, + "args": { + "External id": 1444151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169929.850, "dur": 5.278, + "args": { + "External id": 1444152,"Record function id": 0, "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169931.373, "dur": 3.348, + "args": { + "External id": 1444153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169931.977, "dur": 2.266, + "args": { + "External id": 1444154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169932.922, "dur": 1.245, + "args": { + "External id": 1444155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169938.204, "dur": 7.473, + "args": { + "External id": 1444156,"Record function id": 0, "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169939.808, "dur": 5.435, + "args": { + "External id": 1444157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169940.297, "dur": 4.444, + "args": { + "External id": 1444158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169941.311, "dur": 3.342, + "args": { + "External id": 1444159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169948.750, "dur": 5.553, + "args": { + "External id": 1444160,"Record function id": 0, "Ev Idx": 9535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169950.145, "dur": 3.736, + "args": { + "External id": 1444161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169950.631, "dur": 2.673, + "args": { + "External id": 1444162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169951.907, "dur": 1.321, + "args": { + "External id": 1444163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169957.511, "dur": 5.059, + "args": { + "External id": 1444164,"Record function id": 0, "Ev Idx": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169958.968, "dur": 3.207, + "args": { + "External id": 1444165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169959.403, "dur": 2.280, + "args": { + "External id": 1444166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169960.432, "dur": 1.167, + "args": { + "External id": 1444167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169965.606, "dur": 5.085, + "args": { + "External id": 1444168,"Record function id": 0, "Ev Idx": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169966.871, "dur": 3.421, + "args": { + "External id": 1444169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169967.466, "dur": 2.238, + "args": { + "External id": 1444170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169968.441, "dur": 1.189, + "args": { + "External id": 1444171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169974.136, "dur": 24.094, + "args": { + "External id": 1444172,"Record function id": 0, "Ev Idx": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855169975.386, "dur": 21.758, + "args": { + "External id": 1444173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169975.824, "dur": 20.280, + "args": { + "External id": 1444174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855169976.703, "dur": 18.955, + "args": { + "External id": 1444175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855170004.807, "dur": 64121.709, + "args": { + "External id": 1444176,"Record function id": 0, "Sequence number": 15348914, "Fwd thread id": 1, "Ev Idx": 9551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855170006.857, "dur": 64109.402, + "args": { + "External id": 1444177,"Sequence number": 15348914, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9552 + } + }, + { + "ph": "f", "id": 421, "pid": 2338706, "tid": 2379422, "ts": 6413855170006.857, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413855170039.210, "dur": 76.146, + "args": { + "External id": 1444178,"Record function id": 0, "Ev Idx": 9553 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413855170125.973, "dur": 70.959, + "args": { + "External id": 1444179,"Record function id": 0, "Ev Idx": 9554 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 2338706, "tid": 2379422, + "ts": 6413855170203.597, "dur": 63904.011, + "args": { + "External id": 1444180,"Record function id": 0, "Ev Idx": 9555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855170295.325, "dur": 7.658, + "args": { + "External id": 1444181,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855170313.330, "dur": 4.905, + "args": { + "External id": 1444182,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855170332.645, "dur": 62874.171, + "args": { + "External id": 1444183,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855170347.212, "dur": 62846.013, + "args": { + "External id": 1444184,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855170473.754, "dur": 18.261, + "args": { + "External id": 1444185,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855170512.148, "dur": 62630.645, + "args": { + "External id": 1444186,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855170515.212, "dur": 62626.461, + "args": { + "External id": 1444187,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855170519.819, "dur": 8.385, + "args": { + "External id": 1444188,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855170532.714, "dur": 62603.783, + "args": { + "External id": 1444189,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855233318.301, "dur": 14.350, + "args": { + "External id": 1444190,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855233321.851, "dur": 10.390, + "args": { + "External id": 1444191,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233365.021, "dur": 302.151, + "args": { + "External id": 1444192,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855233395.012, "dur": 267.519, + "args": { + "External id": 1444193,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9568, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855233409.816, "dur": 247.805, + "args": { + "External id": 1444194,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855233686.981, "dur": 2.220, + "args": { + "External id": 1444195,"Record function id": 0, "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": 9570, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233745.865, "dur": 9.063, + "args": { + "External id": 1444196,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233766.654, "dur": 32.487, + "args": { + "External id": 1444197,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233809.369, "dur": 1.683, + "args": { + "External id": 1444198,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233816.765, "dur": 12.932, + "args": { + "External id": 1444199,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233835.586, "dur": 1.161, + "args": { + "External id": 1444200,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233841.602, "dur": 12.800, + "args": { + "External id": 1444201,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233859.537, "dur": 0.931, + "args": { + "External id": 1444202,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233865.251, "dur": 12.185, + "args": { + "External id": 1444203,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233881.943, "dur": 0.780, + "args": { + "External id": 1444204,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233886.981, "dur": 11.945, + "args": { + "External id": 1444205,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233903.518, "dur": 1.086, + "args": { + "External id": 1444206,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233908.685, "dur": 12.122, + "args": { + "External id": 1444207,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233925.489, "dur": 0.968, + "args": { + "External id": 1444208,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233932.939, "dur": 12.402, + "args": { + "External id": 1444209,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233949.193, "dur": 0.849, + "args": { + "External id": 1444210,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233954.093, "dur": 12.040, + "args": { + "External id": 1444211,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855233970.417, "dur": 3.236, + "args": { + "External id": 1444212,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855233995.651, "dur": 16.728, + "args": { + "External id": 1444213,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855234144.115, "dur": 2969.626, + "args": { + "External id": 1444214,"Record function id": 0, "Ev Idx": 9589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413855234165.700, "dur": 1094.035, + "args": { + "External id": 1444215,"Record function id": 0, "Ev Idx": 9590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413855234182.443, "dur": 336.121, + "args": { + "External id": 1444216,"Record function id": 0, "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234280.822, "dur": 4.726, + "args": { + "External id": 1444217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234288.793, "dur": 0.764, + "args": { + "External id": 1444218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234291.586, "dur": 0.934, + "args": { + "External id": 1444219,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234294.559, "dur": 1.138, + "args": { + "External id": 1444220,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234297.105, "dur": 0.929, + "args": { + "External id": 1444221,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234301.536, "dur": 0.857, + "args": { + "External id": 1444222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234304.236, "dur": 0.927, + "args": { + "External id": 1444223,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234306.489, "dur": 3.804, + "args": { + "External id": 1444224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234311.588, "dur": 0.807, + "args": { + "External id": 1444225,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855234316.242, "dur": 0.739, + "args": { + "External id": 1444226,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855234335.057, "dur": 151.644, + "args": { + "External id": 1444227,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855234352.916, "dur": 129.538, + "args": { + "External id": 1444228,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855234371.493, "dur": 15.261, + "args": { + "External id": 1444229,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855234390.636, "dur": 61.194, + "args": { + "External id": 1444230,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855234393.653, "dur": 57.835, + "args": { + "External id": 1444231,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234397.727, "dur": 5.567, + "args": { + "External id": 1444232,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855234405.164, "dur": 45.700, + "args": { + "External id": 1444233,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9608 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 2338706, "tid": 2379422, + "ts": 6413855234612.551, "dur": 639.167, + "args": { + "External id": 1444234,"Record function id": 0, "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413855234629.665, "dur": 608.184, + "args": { + "External id": 1444235,"Record function id": 0, "Ev Idx": 9610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855234700.198, "dur": 4.757, + "args": { + "External id": 1444236,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855234719.595, "dur": 27.979, + "args": { + "External id": 1444237,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234724.402, "dur": 1.521, + "args": { + "External id": 1444238,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234728.387, "dur": 0.415, + "args": { + "External id": 1444239,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234729.891, "dur": 2.534, + "args": { + "External id": 1444240,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234734.050, "dur": 0.377, + "args": { + "External id": 1444241,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234736.040, "dur": 0.728, + "args": { + "External id": 1444242,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234737.802, "dur": 0.651, + "args": { + "External id": 1444243,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234740.100, "dur": 0.506, + "args": { + "External id": 1444244,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234742.139, "dur": 0.445, + "args": { + "External id": 1444245,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234743.620, "dur": 0.441, + "args": { + "External id": 1444246,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855234758.817, "dur": 43.574, + "args": { + "External id": 1444247,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855234831.138, "dur": 105.351, + "args": { + "External id": 1444248,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855234840.761, "dur": 3.058, + "args": { + "External id": 1444249,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855234849.004, "dur": 12.816, + "args": { + "External id": 1444250,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855234853.468, "dur": 7.834, + "args": { + "External id": 1444251,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234857.485, "dur": 2.711, + "args": { + "External id": 1444252,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855234867.778, "dur": 22.899, + "args": { + "External id": 1444253,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234869.994, "dur": 0.554, + "args": { + "External id": 1444254,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234871.642, "dur": 0.566, + "args": { + "External id": 1444255,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234874.082, "dur": 0.538, + "args": { + "External id": 1444256,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234876.088, "dur": 0.618, + "args": { + "External id": 1444257,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234877.667, "dur": 0.686, + "args": { + "External id": 1444258,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234880.017, "dur": 0.683, + "args": { + "External id": 1444259,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234882.080, "dur": 0.324, + "args": { + "External id": 1444260,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234883.367, "dur": 2.673, + "args": { + "External id": 1444261,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855234887.615, "dur": 0.425, + "args": { + "External id": 1444262,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855234899.896, "dur": 29.467, + "args": { + "External id": 1444263,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855234997.543, "dur": 158.137, + "args": { + "External id": 1444264,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855235023.438, "dur": 127.847, + "args": { + "External id": 1444265,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9640, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855235034.206, "dur": 112.434, + "args": { + "External id": 1444266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855235176.183, "dur": 2.232, + "args": { + "External id": 1444267,"Record function id": 0, "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": 9642, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855235267.744, "dur": 1818.392, + "args": { + "External id": 1444268,"Sequence number": 15348913, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9643 + } + }, + { + "ph": "f", "id": 422, "pid": 2338706, "tid": 2379422, "ts": 6413855235267.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235383.241, "dur": 106.849, + "args": { + "External id": 1444269,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855235532.335, "dur": 40.481, + "args": { + "External id": 1444270,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235592.601, "dur": 49.962, + "args": { + "External id": 1444271,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235652.872, "dur": 31.043, + "args": { + "External id": 1444272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235689.993, "dur": 32.079, + "args": { + "External id": 1444273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235728.469, "dur": 26.842, + "args": { + "External id": 1444274,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235763.209, "dur": 28.549, + "args": { + "External id": 1444275,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855235816.755, "dur": 24.497, + "args": { + "External id": 1444276,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855235861.325, "dur": 29.910, + "args": { + "External id": 1444277,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855235913.329, "dur": 20.030, + "args": { + "External id": 1444278,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855235945.561, "dur": 15.255, + "args": { + "External id": 1444279,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855235971.905, "dur": 59.072, + "args": { + "External id": 1444280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236036.450, "dur": 70.795, + "args": { + "External id": 1444281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855236139.567, "dur": 259.177, + "args": { + "External id": 1444282,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855236224.849, "dur": 6.321, + "args": { + "External id": 1444283,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855236233.225, "dur": 3.166, + "args": { + "External id": 1444284,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855236237.972, "dur": 4.185, + "args": { + "External id": 1444285,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855236243.135, "dur": 2.624, + "args": { + "External id": 1444286,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855236293.997, "dur": 5.091, + "args": { + "External id": 1444287,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855236295.815, "dur": 3.113, + "args": { + "External id": 1444288,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855236300.953, "dur": 34.071, + "args": { + "External id": 1444289,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855236306.893, "dur": 1.743, + "args": { + "External id": 1444290,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855236336.930, "dur": 2.163, + "args": { + "External id": 1444291,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855236338.045, "dur": 0.965, + "args": { + "External id": 1444292,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855236340.115, "dur": 16.780, + "args": { + "External id": 1444293,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855236342.948, "dur": 0.860, + "args": { + "External id": 1444294,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855236454.978, "dur": 30.658, + "args": { + "External id": 1444295,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855236505.357, "dur": 19.487, + "args": { + "External id": 1444296,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236533.690, "dur": 47.980, + "args": { + "External id": 1444297,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236589.196, "dur": 40.718, + "args": { + "External id": 1444298,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236641.421, "dur": 23.003, + "args": { + "External id": 1444299,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236670.500, "dur": 32.084, + "args": { + "External id": 1444300,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236710.085, "dur": 28.568, + "args": { + "External id": 1444301,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855236746.614, "dur": 31.066, + "args": { + "External id": 1444302,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855236796.122, "dur": 40.079, + "args": { + "External id": 1444303,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855236858.722, "dur": 25.064, + "args": { + "External id": 1444304,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855236899.140, "dur": 17.080, + "args": { + "External id": 1444305,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855236942.670, "dur": 14.818, + "args": { + "External id": 1444306,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855236972.671, "dur": 46.472, + "args": { + "External id": 1444307,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237137.169, "dur": 16.810, + "args": { + "External id": 1444308,"Record function id": 0, "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237141.601, "dur": 11.367, + "args": { + "External id": 1444309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237146.016, "dur": 6.018, + "args": { + "External id": 1444310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237147.685, "dur": 4.232, + "args": { + "External id": 1444311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237157.867, "dur": 6.674, + "args": { + "External id": 1444312,"Record function id": 0, "Ev Idx": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237159.842, "dur": 4.180, + "args": { + "External id": 1444313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237160.515, "dur": 2.710, + "args": { + "External id": 1444314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237161.985, "dur": 1.148, + "args": { + "External id": 1444315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237167.796, "dur": 5.607, + "args": { + "External id": 1444316,"Record function id": 0, "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237169.753, "dur": 3.201, + "args": { + "External id": 1444317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237170.288, "dur": 2.079, + "args": { + "External id": 1444318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237171.089, "dur": 1.205, + "args": { + "External id": 1444319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237176.714, "dur": 5.088, + "args": { + "External id": 1444320,"Record function id": 0, "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237178.055, "dur": 3.285, + "args": { + "External id": 1444321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237178.531, "dur": 2.252, + "args": { + "External id": 1444322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237179.428, "dur": 1.284, + "args": { + "External id": 1444323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237184.918, "dur": 7.637, + "args": { + "External id": 1444324,"Record function id": 0, "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237186.255, "dur": 5.852, + "args": { + "External id": 1444325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237187.114, "dur": 4.344, + "args": { + "External id": 1444326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237187.877, "dur": 3.485, + "args": { + "External id": 1444327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237195.672, "dur": 5.443, + "args": { + "External id": 1444328,"Record function id": 0, "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237197.237, "dur": 3.414, + "args": { + "External id": 1444329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237197.682, "dur": 2.280, + "args": { + "External id": 1444330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237198.550, "dur": 1.332, + "args": { + "External id": 1444331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237204.476, "dur": 5.919, + "args": { + "External id": 1444332,"Record function id": 0, "Ev Idx": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237205.850, "dur": 4.128, + "args": { + "External id": 1444333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237206.482, "dur": 3.080, + "args": { + "External id": 1444334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237208.249, "dur": 1.233, + "args": { + "External id": 1444335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237214.161, "dur": 5.598, + "args": { + "External id": 1444336,"Record function id": 0, "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237215.907, "dur": 3.427, + "args": { + "External id": 1444337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237216.368, "dur": 2.355, + "args": { + "External id": 1444338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237217.494, "dur": 1.155, + "args": { + "External id": 1444339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237223.376, "dur": 5.253, + "args": { + "External id": 1444340,"Record function id": 0, "Ev Idx": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855237224.680, "dur": 3.529, + "args": { + "External id": 1444341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237225.100, "dur": 2.689, + "args": { + "External id": 1444342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855237225.959, "dur": 1.758, + "args": { + "External id": 1444343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855237233.334, "dur": 66527.773, + "args": { + "External id": 1444344,"Record function id": 0, "Sequence number": 15348912, "Fwd thread id": 1, "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855237234.681, "dur": 66516.426, + "args": { + "External id": 1444345,"Sequence number": 15348912, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9720 + } + }, + { + "ph": "f", "id": 423, "pid": 2338706, "tid": 2379422, "ts": 6413855237234.681, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413855237267.744, "dur": 42.534, + "args": { + "External id": 1444346,"Record function id": 0, "Ev Idx": 9721 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413855237318.771, "dur": 67.480, + "args": { + "External id": 1444347,"Record function id": 0, "Ev Idx": 9722 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 2338706, "tid": 2379422, + "ts": 6413855237391.739, "dur": 66351.598, + "args": { + "External id": 1444348,"Record function id": 0, "Ev Idx": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855237484.034, "dur": 7.331, + "args": { + "External id": 1444349,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855237500.738, "dur": 4.781, + "args": { + "External id": 1444350,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855237520.202, "dur": 65196.558, + "args": { + "External id": 1444351,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855237534.605, "dur": 65168.460, + "args": { + "External id": 1444352,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855237739.175, "dur": 22.837, + "args": { + "External id": 1444353,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855237783.861, "dur": 64872.181, + "args": { + "External id": 1444354,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855237786.747, "dur": 64868.333, + "args": { + "External id": 1444355,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855237791.839, "dur": 9.826, + "args": { + "External id": 1444356,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855237805.754, "dur": 64844.755, + "args": { + "External id": 1444357,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855302829.674, "dur": 12.459, + "args": { + "External id": 1444358,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855302833.186, "dur": 8.534, + "args": { + "External id": 1444359,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855302872.513, "dur": 470.426, + "args": { + "External id": 1444360,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855302906.327, "dur": 430.672, + "args": { + "External id": 1444361,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9736, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855302918.014, "dur": 411.514, + "args": { + "External id": 1444362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855303367.474, "dur": 2.470, + "args": { + "External id": 1444363,"Record function id": 0, "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": 9738, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303434.387, "dur": 9.200, + "args": { + "External id": 1444364,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303456.136, "dur": 35.895, + "args": { + "External id": 1444365,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303502.730, "dur": 1.749, + "args": { + "External id": 1444366,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303511.486, "dur": 13.891, + "args": { + "External id": 1444367,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303531.044, "dur": 1.048, + "args": { + "External id": 1444368,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303536.333, "dur": 12.873, + "args": { + "External id": 1444369,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303553.965, "dur": 1.055, + "args": { + "External id": 1444370,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303559.123, "dur": 11.445, + "args": { + "External id": 1444371,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303575.295, "dur": 0.713, + "args": { + "External id": 1444372,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303579.963, "dur": 13.256, + "args": { + "External id": 1444373,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303597.825, "dur": 1.008, + "args": { + "External id": 1444374,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303602.834, "dur": 12.132, + "args": { + "External id": 1444375,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303619.931, "dur": 0.680, + "args": { + "External id": 1444376,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303624.321, "dur": 13.673, + "args": { + "External id": 1444377,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303642.422, "dur": 0.798, + "args": { + "External id": 1444378,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303647.288, "dur": 11.406, + "args": { + "External id": 1444379,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855303665.879, "dur": 3.481, + "args": { + "External id": 1444380,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855303672.886, "dur": 12.620, + "args": { + "External id": 1444381,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855303775.978, "dur": 2961.057, + "args": { + "External id": 1444382,"Record function id": 0, "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413855303796.783, "dur": 1076.253, + "args": { + "External id": 1444383,"Record function id": 0, "Ev Idx": 9758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413855303812.382, "dur": 389.845, + "args": { + "External id": 1444384,"Record function id": 0, "Ev Idx": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303899.382, "dur": 4.417, + "args": { + "External id": 1444385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303907.703, "dur": 1.188, + "args": { + "External id": 1444386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303910.619, "dur": 0.877, + "args": { + "External id": 1444387,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303913.719, "dur": 1.011, + "args": { + "External id": 1444388,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303916.512, "dur": 1.052, + "args": { + "External id": 1444389,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303919.196, "dur": 1.110, + "args": { + "External id": 1444390,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303924.090, "dur": 1.044, + "args": { + "External id": 1444391,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303926.825, "dur": 4.071, + "args": { + "External id": 1444392,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303932.356, "dur": 1.009, + "args": { + "External id": 1444393,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855303935.247, "dur": 0.512, + "args": { + "External id": 1444394,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855303960.184, "dur": 205.535, + "args": { + "External id": 1444395,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855303977.351, "dur": 182.531, + "args": { + "External id": 1444396,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855304010.697, "dur": 16.040, + "args": { + "External id": 1444397,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855304031.069, "dur": 99.311, + "args": { + "External id": 1444398,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855304034.195, "dur": 95.875, + "args": { + "External id": 1444399,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304038.403, "dur": 5.834, + "args": { + "External id": 1444400,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855304046.344, "dur": 82.536, + "args": { + "External id": 1444401,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9776 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 2338706, "tid": 2379422, + "ts": 6413855304294.992, "dur": 570.393, + "args": { + "External id": 1444402,"Record function id": 0, "Ev Idx": 9777 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413855304314.051, "dur": 538.920, + "args": { + "External id": 1444403,"Record function id": 0, "Ev Idx": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855304380.959, "dur": 6.140, + "args": { + "External id": 1444404,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855304402.648, "dur": 30.671, + "args": { + "External id": 1444405,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304407.847, "dur": 2.020, + "args": { + "External id": 1444406,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304412.299, "dur": 0.750, + "args": { + "External id": 1444407,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304414.855, "dur": 2.793, + "args": { + "External id": 1444408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304418.592, "dur": 0.540, + "args": { + "External id": 1444409,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304421.194, "dur": 0.302, + "args": { + "External id": 1444410,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304423.103, "dur": 0.371, + "args": { + "External id": 1444411,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304424.782, "dur": 0.409, + "args": { + "External id": 1444412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304426.534, "dur": 0.628, + "args": { + "External id": 1444413,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304429.016, "dur": 0.372, + "args": { + "External id": 1444414,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855304445.252, "dur": 42.298, + "args": { + "External id": 1444415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855304518.226, "dur": 106.746, + "args": { + "External id": 1444416,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855304528.992, "dur": 3.196, + "args": { + "External id": 1444417,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855304537.329, "dur": 11.887, + "args": { + "External id": 1444418,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855304541.642, "dur": 7.174, + "args": { + "External id": 1444419,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304545.408, "dur": 2.282, + "args": { + "External id": 1444420,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855304555.589, "dur": 20.973, + "args": { + "External id": 1444421,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304557.422, "dur": 0.460, + "args": { + "External id": 1444422,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304559.343, "dur": 0.477, + "args": { + "External id": 1444423,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304561.085, "dur": 0.495, + "args": { + "External id": 1444424,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304563.281, "dur": 0.334, + "args": { + "External id": 1444425,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304565.170, "dur": 0.332, + "args": { + "External id": 1444426,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304566.722, "dur": 0.436, + "args": { + "External id": 1444427,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304568.655, "dur": 0.367, + "args": { + "External id": 1444428,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304570.275, "dur": 2.284, + "args": { + "External id": 1444429,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855304573.636, "dur": 0.492, + "args": { + "External id": 1444430,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855304587.241, "dur": 30.495, + "args": { + "External id": 1444431,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855304667.398, "dur": 117.057, + "args": { + "External id": 1444432,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855304692.757, "dur": 88.214, + "args": { + "External id": 1444433,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9808, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855304702.265, "dur": 74.696, + "args": { + "External id": 1444434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855304800.779, "dur": 1.624, + "args": { + "External id": 1444435,"Record function id": 0, "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": 9810, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855304879.973, "dur": 1833.720, + "args": { + "External id": 1444436,"Sequence number": 15348911, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9811 + } + }, + { + "ph": "f", "id": 424, "pid": 2338706, "tid": 2379422, "ts": 6413855304879.973, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305013.330, "dur": 153.781, + "args": { + "External id": 1444437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855305217.610, "dur": 45.280, + "args": { + "External id": 1444438,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305284.332, "dur": 51.977, + "args": { + "External id": 1444439,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305347.096, "dur": 32.411, + "args": { + "External id": 1444440,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305385.750, "dur": 32.351, + "args": { + "External id": 1444441,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305424.956, "dur": 27.340, + "args": { + "External id": 1444442,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305461.736, "dur": 28.981, + "args": { + "External id": 1444443,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855305515.804, "dur": 23.277, + "args": { + "External id": 1444444,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855305557.388, "dur": 30.334, + "args": { + "External id": 1444445,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855305608.671, "dur": 20.745, + "args": { + "External id": 1444446,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855305643.405, "dur": 15.460, + "args": { + "External id": 1444447,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305670.151, "dur": 35.685, + "args": { + "External id": 1444448,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855305709.509, "dur": 33.598, + "args": { + "External id": 1444449,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855305772.186, "dur": 333.474, + "args": { + "External id": 1444450,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855305856.188, "dur": 6.273, + "args": { + "External id": 1444451,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855305864.845, "dur": 2.795, + "args": { + "External id": 1444452,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855305869.228, "dur": 4.988, + "args": { + "External id": 1444453,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855305875.321, "dur": 2.415, + "args": { + "External id": 1444454,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855305925.517, "dur": 5.161, + "args": { + "External id": 1444455,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855305927.712, "dur": 2.790, + "args": { + "External id": 1444456,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855305932.854, "dur": 37.645, + "args": { + "External id": 1444457,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855305938.755, "dur": 1.977, + "args": { + "External id": 1444458,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855305972.308, "dur": 25.336, + "args": { + "External id": 1444459,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855305995.611, "dur": 1.603, + "args": { + "External id": 1444460,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855305999.566, "dur": 23.762, + "args": { + "External id": 1444461,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 9836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855306002.336, "dur": 0.814, + "args": { + "External id": 1444462,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 9837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855306147.445, "dur": 32.692, + "args": { + "External id": 1444463,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855306198.148, "dur": 18.822, + "args": { + "External id": 1444464,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855306225.950, "dur": 49.989, + "args": { + "External id": 1444465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855306284.445, "dur": 54.465, + "args": { + "External id": 1444466,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855306357.798, "dur": 27.464, + "args": { + "External id": 1444467,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 9842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855306391.985, "dur": 36.209, + "args": { + "External id": 1444468,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 9843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855306436.031, "dur": 30.985, + "args": { + "External id": 1444469,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855306474.431, "dur": 30.151, + "args": { + "External id": 1444470,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855306526.701, "dur": 24.705, + "args": { + "External id": 1444471,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 9846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855306567.190, "dur": 26.816, + "args": { + "External id": 1444472,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855306607.180, "dur": 16.475, + "args": { + "External id": 1444473,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855306637.728, "dur": 14.938, + "args": { + "External id": 1444474,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855306664.827, "dur": 16.514, + "args": { + "External id": 1444475,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 9850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306760.854, "dur": 16.823, + "args": { + "External id": 1444476,"Record function id": 0, "Ev Idx": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306764.754, "dur": 11.969, + "args": { + "External id": 1444477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306769.549, "dur": 6.271, + "args": { + "External id": 1444478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306771.338, "dur": 4.370, + "args": { + "External id": 1444479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306781.482, "dur": 5.628, + "args": { + "External id": 1444480,"Record function id": 0, "Ev Idx": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306783.022, "dur": 3.606, + "args": { + "External id": 1444481,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306783.672, "dur": 2.335, + "args": { + "External id": 1444482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306784.596, "dur": 1.274, + "args": { + "External id": 1444483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306790.568, "dur": 5.125, + "args": { + "External id": 1444484,"Record function id": 0, "Ev Idx": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306792.188, "dur": 3.097, + "args": { + "External id": 1444485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306792.655, "dur": 2.194, + "args": { + "External id": 1444486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306793.314, "dur": 1.436, + "args": { + "External id": 1444487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 9862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306798.832, "dur": 4.745, + "args": { + "External id": 1444488,"Record function id": 0, "Ev Idx": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306800.092, "dur": 3.075, + "args": { + "External id": 1444489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306800.537, "dur": 2.217, + "args": { + "External id": 1444490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306801.529, "dur": 1.141, + "args": { + "External id": 1444491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 9866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306806.684, "dur": 7.167, + "args": { + "External id": 1444492,"Record function id": 0, "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306808.290, "dur": 5.140, + "args": { + "External id": 1444493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306808.714, "dur": 4.248, + "args": { + "External id": 1444494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306809.612, "dur": 3.261, + "args": { + "External id": 1444495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306816.928, "dur": 5.361, + "args": { + "External id": 1444496,"Record function id": 0, "Ev Idx": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306818.616, "dur": 3.276, + "args": { + "External id": 1444497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306819.043, "dur": 2.194, + "args": { + "External id": 1444498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306819.926, "dur": 1.242, + "args": { + "External id": 1444499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 9874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306825.482, "dur": 5.066, + "args": { + "External id": 1444500,"Record function id": 0, "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306827.065, "dur": 3.070, + "args": { + "External id": 1444501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306827.540, "dur": 1.908, + "args": { + "External id": 1444502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306828.216, "dur": 1.128, + "args": { + "External id": 1444503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306833.800, "dur": 5.259, + "args": { + "External id": 1444504,"Record function id": 0, "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306835.220, "dur": 3.429, + "args": { + "External id": 1444505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306835.688, "dur": 2.385, + "args": { + "External id": 1444506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306836.838, "dur": 1.142, + "args": { + "External id": 1444507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 9882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306842.546, "dur": 4.159, + "args": { + "External id": 1444508,"Record function id": 0, "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855306843.654, "dur": 2.639, + "args": { + "External id": 1444509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306844.139, "dur": 1.594, + "args": { + "External id": 1444510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855306844.678, "dur": 0.972, + "args": { + "External id": 1444511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 9886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855306851.475, "dur": 64478.245, + "args": { + "External id": 1444512,"Record function id": 0, "Sequence number": 15348910, "Fwd thread id": 1, "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855306853.133, "dur": 64467.342, + "args": { + "External id": 1444513,"Sequence number": 15348910, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9888 + } + }, + { + "ph": "f", "id": 425, "pid": 2338706, "tid": 2379422, "ts": 6413855306853.133, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413855306883.529, "dur": 39.479, + "args": { + "External id": 1444514,"Record function id": 0, "Ev Idx": 9889 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413855306930.879, "dur": 90.843, + "args": { + "External id": 1444515,"Record function id": 0, "Ev Idx": 9890 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 2338706, "tid": 2379422, + "ts": 6413855307029.795, "dur": 64281.781, + "args": { + "External id": 1444516,"Record function id": 0, "Ev Idx": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855307166.544, "dur": 7.532, + "args": { + "External id": 1444517,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855307185.006, "dur": 5.012, + "args": { + "External id": 1444518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855307204.959, "dur": 63102.067, + "args": { + "External id": 1444519,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855307218.886, "dur": 63074.295, + "args": { + "External id": 1444520,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 9895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855307399.527, "dur": 18.926, + "args": { + "External id": 1444521,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855307438.564, "dur": 62810.984, + "args": { + "External id": 1444522,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 9897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855307441.523, "dur": 62807.020, + "args": { + "External id": 1444523,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 9898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855307446.406, "dur": 8.309, + "args": { + "External id": 1444524,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855307457.058, "dur": 62786.473, + "args": { + "External id": 1444525,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 9900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855370421.182, "dur": 13.581, + "args": { + "External id": 1444526,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 9901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855370424.773, "dur": 9.654, + "args": { + "External id": 1444527,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855370465.658, "dur": 392.688, + "args": { + "External id": 1444528,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 9903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855370494.964, "dur": 358.302, + "args": { + "External id": 1444529,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9904, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855370507.526, "dur": 340.257, + "args": { + "External id": 1444530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 9905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855370879.969, "dur": 2.072, + "args": { + "External id": 1444531,"Record function id": 0, "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": 9906, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855370939.730, "dur": 8.683, + "args": { + "External id": 1444532,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855370960.727, "dur": 55.093, + "args": { + "External id": 1444533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371028.854, "dur": 2.220, + "args": { + "External id": 1444534,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371037.312, "dur": 15.400, + "args": { + "External id": 1444535,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371093.287, "dur": 1.875, + "args": { + "External id": 1444536,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371101.021, "dur": 16.148, + "args": { + "External id": 1444537,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371122.302, "dur": 1.041, + "args": { + "External id": 1444538,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371127.719, "dur": 11.128, + "args": { + "External id": 1444539,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 9914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371143.416, "dur": 0.772, + "args": { + "External id": 1444540,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371149.126, "dur": 12.382, + "args": { + "External id": 1444541,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 9916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371165.132, "dur": 1.015, + "args": { + "External id": 1444542,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371170.281, "dur": 11.693, + "args": { + "External id": 1444543,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 9918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371186.439, "dur": 0.950, + "args": { + "External id": 1444544,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371191.934, "dur": 11.722, + "args": { + "External id": 1444545,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371209.926, "dur": 0.866, + "args": { + "External id": 1444546,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371215.076, "dur": 11.154, + "args": { + "External id": 1444547,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 9922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371230.305, "dur": 2.805, + "args": { + "External id": 1444548,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371237.151, "dur": 12.041, + "args": { + "External id": 1444549,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 9924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855371347.085, "dur": 2999.875, + "args": { + "External id": 1444550,"Record function id": 0, "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413855371369.573, "dur": 1082.245, + "args": { + "External id": 1444551,"Record function id": 0, "Ev Idx": 9926 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413855371387.004, "dur": 322.616, + "args": { + "External id": 1444552,"Record function id": 0, "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371477.438, "dur": 4.280, + "args": { + "External id": 1444553,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 9928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371484.814, "dur": 1.022, + "args": { + "External id": 1444554,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371487.562, "dur": 0.724, + "args": { + "External id": 1444555,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371490.310, "dur": 1.155, + "args": { + "External id": 1444556,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371493.220, "dur": 0.886, + "args": { + "External id": 1444557,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 9932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371497.847, "dur": 0.998, + "args": { + "External id": 1444558,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 9933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371500.497, "dur": 0.856, + "args": { + "External id": 1444559,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 9934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371503.019, "dur": 3.977, + "args": { + "External id": 1444560,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371508.487, "dur": 0.874, + "args": { + "External id": 1444561,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855371512.890, "dur": 0.695, + "args": { + "External id": 1444562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 9937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855371531.061, "dur": 147.833, + "args": { + "External id": 1444563,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855371548.496, "dur": 125.838, + "args": { + "External id": 1444564,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 9939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855371564.878, "dur": 15.711, + "args": { + "External id": 1444565,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855371584.650, "dur": 62.453, + "args": { + "External id": 1444566,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 9941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855371587.247, "dur": 59.515, + "args": { + "External id": 1444567,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 9942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371591.774, "dur": 5.492, + "args": { + "External id": 1444568,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371599.047, "dur": 47.112, + "args": { + "External id": 1444569,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 9944 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 2338706, "tid": 2379422, + "ts": 6413855371798.933, "dur": 645.108, + "args": { + "External id": 1444570,"Record function id": 0, "Ev Idx": 9945 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413855371815.441, "dur": 615.523, + "args": { + "External id": 1444571,"Record function id": 0, "Ev Idx": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855371875.649, "dur": 4.983, + "args": { + "External id": 1444572,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855371895.692, "dur": 30.128, + "args": { + "External id": 1444573,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371901.168, "dur": 1.707, + "args": { + "External id": 1444574,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371904.328, "dur": 0.534, + "args": { + "External id": 1444575,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371906.860, "dur": 2.755, + "args": { + "External id": 1444576,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371911.349, "dur": 0.354, + "args": { + "External id": 1444577,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371913.170, "dur": 0.664, + "args": { + "External id": 1444578,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371915.885, "dur": 0.572, + "args": { + "External id": 1444579,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371918.258, "dur": 0.331, + "args": { + "External id": 1444580,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371919.677, "dur": 0.577, + "args": { + "External id": 1444581,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855371922.035, "dur": 0.340, + "args": { + "External id": 1444582,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855371937.226, "dur": 59.992, + "args": { + "External id": 1444583,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855372030.600, "dur": 159.991, + "args": { + "External id": 1444584,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 9959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855372042.149, "dur": 4.699, + "args": { + "External id": 1444585,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855372052.331, "dur": 47.208, + "args": { + "External id": 1444586,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855372089.277, "dur": 9.818, + "args": { + "External id": 1444587,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 9962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372093.783, "dur": 3.605, + "args": { + "External id": 1444588,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 9963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855372111.897, "dur": 24.591, + "args": { + "External id": 1444589,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 9964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372114.553, "dur": 0.542, + "args": { + "External id": 1444590,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372116.694, "dur": 0.560, + "args": { + "External id": 1444591,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372118.758, "dur": 0.416, + "args": { + "External id": 1444592,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372120.233, "dur": 0.577, + "args": { + "External id": 1444593,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372122.541, "dur": 0.425, + "args": { + "External id": 1444594,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372125.182, "dur": 0.302, + "args": { + "External id": 1444595,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372126.917, "dur": 0.343, + "args": { + "External id": 1444596,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372129.465, "dur": 2.613, + "args": { + "External id": 1444597,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855372133.715, "dur": 0.279, + "args": { + "External id": 1444598,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 9973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855372148.186, "dur": 34.547, + "args": { + "External id": 1444599,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 9974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855372238.338, "dur": 119.724, + "args": { + "External id": 1444600,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 9975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855372265.908, "dur": 88.844, + "args": { + "External id": 1444601,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 9976, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855372276.138, "dur": 74.454, + "args": { + "External id": 1444602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 9977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855372375.949, "dur": 1.953, + "args": { + "External id": 1444603,"Record function id": 0, "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": 9978, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855372459.527, "dur": 1861.110, + "args": { + "External id": 1444604,"Sequence number": 15348909, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 9979 + } + }, + { + "ph": "f", "id": 426, "pid": 2338706, "tid": 2379422, "ts": 6413855372459.527, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855372574.782, "dur": 109.305, + "args": { + "External id": 1444605,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 9980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855372724.320, "dur": 41.596, + "args": { + "External id": 1444606,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 9981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855372785.769, "dur": 49.306, + "args": { + "External id": 1444607,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 9982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855372844.821, "dur": 30.948, + "args": { + "External id": 1444608,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855372882.274, "dur": 33.360, + "args": { + "External id": 1444609,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855372922.501, "dur": 27.617, + "args": { + "External id": 1444610,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 9985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855372959.593, "dur": 47.149, + "args": { + "External id": 1444611,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 9986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855373037.911, "dur": 60.875, + "args": { + "External id": 1444612,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 9987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855373122.587, "dur": 32.473, + "args": { + "External id": 1444613,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 9988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855373179.402, "dur": 19.531, + "args": { + "External id": 1444614,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 9989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855373214.147, "dur": 15.318, + "args": { + "External id": 1444615,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 9990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373240.816, "dur": 42.938, + "args": { + "External id": 1444616,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 9991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373287.818, "dur": 34.483, + "args": { + "External id": 1444617,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 9992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855373351.819, "dur": 276.798, + "args": { + "External id": 1444618,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 9993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855373433.375, "dur": 6.596, + "args": { + "External id": 1444619,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855373442.812, "dur": 2.863, + "args": { + "External id": 1444620,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855373447.314, "dur": 2.875, + "args": { + "External id": 1444621,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855373451.628, "dur": 4.938, + "args": { + "External id": 1444622,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855373501.638, "dur": 5.494, + "args": { + "External id": 1444623,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855373504.065, "dur": 2.919, + "args": { + "External id": 1444624,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 9999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855373528.486, "dur": 34.231, + "args": { + "External id": 1444625,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855373534.295, "dur": 1.950, + "args": { + "External id": 1444626,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855373564.188, "dur": 2.058, + "args": { + "External id": 1444627,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855373565.590, "dur": 0.569, + "args": { + "External id": 1444628,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855373567.199, "dur": 17.093, + "args": { + "External id": 1444629,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855373569.561, "dur": 0.546, + "args": { + "External id": 1444630,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855373664.956, "dur": 27.871, + "args": { + "External id": 1444631,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855373712.411, "dur": 18.456, + "args": { + "External id": 1444632,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373739.337, "dur": 41.815, + "args": { + "External id": 1444633,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373789.070, "dur": 39.901, + "args": { + "External id": 1444634,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373840.132, "dur": 23.187, + "args": { + "External id": 1444635,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373870.385, "dur": 47.383, + "args": { + "External id": 1444636,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855373933.265, "dur": 41.875, + "args": { + "External id": 1444637,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855374005.813, "dur": 39.501, + "args": { + "External id": 1444638,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855374106.603, "dur": 29.834, + "args": { + "External id": 1444639,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855374158.458, "dur": 27.818, + "args": { + "External id": 1444640,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855374202.056, "dur": 18.868, + "args": { + "External id": 1444641,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855374236.276, "dur": 17.233, + "args": { + "External id": 1444642,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855374266.584, "dur": 18.646, + "args": { + "External id": 1444643,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374370.449, "dur": 16.876, + "args": { + "External id": 1444644,"Record function id": 0, "Ev Idx": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374374.641, "dur": 11.690, + "args": { + "External id": 1444645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374379.472, "dur": 5.885, + "args": { + "External id": 1444646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374381.166, "dur": 4.074, + "args": { + "External id": 1444647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374391.417, "dur": 6.149, + "args": { + "External id": 1444648,"Record function id": 0, "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374393.330, "dur": 3.747, + "args": { + "External id": 1444649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374394.106, "dur": 2.465, + "args": { + "External id": 1444650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374395.240, "dur": 1.220, + "args": { + "External id": 1444651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374401.052, "dur": 5.472, + "args": { + "External id": 1444652,"Record function id": 0, "Ev Idx": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374402.552, "dur": 3.532, + "args": { + "External id": 1444653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374403.222, "dur": 2.415, + "args": { + "External id": 1444654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374404.349, "dur": 1.203, + "args": { + "External id": 1444655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374409.669, "dur": 4.908, + "args": { + "External id": 1444656,"Record function id": 0, "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374410.958, "dur": 3.191, + "args": { + "External id": 1444657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374411.540, "dur": 2.208, + "args": { + "External id": 1444658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374412.631, "dur": 1.040, + "args": { + "External id": 1444659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374417.765, "dur": 7.521, + "args": { + "External id": 1444660,"Record function id": 0, "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374419.301, "dur": 5.552, + "args": { + "External id": 1444661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374419.802, "dur": 4.375, + "args": { + "External id": 1444662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374420.685, "dur": 3.397, + "args": { + "External id": 1444663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374428.378, "dur": 5.501, + "args": { + "External id": 1444664,"Record function id": 0, "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374430.078, "dur": 3.364, + "args": { + "External id": 1444665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374430.576, "dur": 2.388, + "args": { + "External id": 1444666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374431.619, "dur": 1.270, + "args": { + "External id": 1444667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374437.491, "dur": 5.797, + "args": { + "External id": 1444668,"Record function id": 0, "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374439.270, "dur": 3.606, + "args": { + "External id": 1444669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374440.095, "dur": 2.375, + "args": { + "External id": 1444670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374441.182, "dur": 1.204, + "args": { + "External id": 1444671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374446.346, "dur": 5.940, + "args": { + "External id": 1444672,"Record function id": 0, "Ev Idx": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374447.946, "dur": 3.919, + "args": { + "External id": 1444673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374448.711, "dur": 2.560, + "args": { + "External id": 1444674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374450.084, "dur": 1.111, + "args": { + "External id": 1444675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374455.318, "dur": 4.846, + "args": { + "External id": 1444676,"Record function id": 0, "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855374456.756, "dur": 2.953, + "args": { + "External id": 1444677,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374457.228, "dur": 2.050, + "args": { + "External id": 1444678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855374458.090, "dur": 1.114, + "args": { + "External id": 1444679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855374464.689, "dur": 64503.783, + "args": { + "External id": 1444680,"Record function id": 0, "Sequence number": 15348908, "Fwd thread id": 1, "Ev Idx": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855374466.311, "dur": 64492.907, + "args": { + "External id": 1444681,"Sequence number": 15348908, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10056 + } + }, + { + "ph": "f", "id": 427, "pid": 2338706, "tid": 2379422, "ts": 6413855374466.311, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413855374497.003, "dur": 40.906, + "args": { + "External id": 1444682,"Record function id": 0, "Ev Idx": 10057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413855374546.708, "dur": 68.625, + "args": { + "External id": 1444683,"Record function id": 0, "Ev Idx": 10058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 2338706, "tid": 2379422, + "ts": 6413855374621.331, "dur": 64329.727, + "args": { + "External id": 1444684,"Record function id": 0, "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855374710.589, "dur": 7.268, + "args": { + "External id": 1444685,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855374727.507, "dur": 4.632, + "args": { + "External id": 1444686,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855374746.374, "dur": 63195.359, + "args": { + "External id": 1444687,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855374760.621, "dur": 63167.705, + "args": { + "External id": 1444688,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855374885.487, "dur": 19.274, + "args": { + "External id": 1444689,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855374924.320, "dur": 62954.216, + "args": { + "External id": 1444690,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855374927.487, "dur": 62949.896, + "args": { + "External id": 1444691,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855374932.296, "dur": 8.537, + "args": { + "External id": 1444692,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855374943.295, "dur": 62928.679, + "args": { + "External id": 1444693,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855438099.983, "dur": 17.588, + "args": { + "External id": 1444694,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855438105.594, "dur": 11.290, + "args": { + "External id": 1444695,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438151.360, "dur": 383.495, + "args": { + "External id": 1444696,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855438183.108, "dur": 346.584, + "args": { + "External id": 1444697,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10072, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855438196.345, "dur": 328.147, + "args": { + "External id": 1444698,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855438577.578, "dur": 2.450, + "args": { + "External id": 1444699,"Record function id": 0, "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": 10074, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438643.755, "dur": 7.008, + "args": { + "External id": 1444700,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438664.459, "dur": 38.346, + "args": { + "External id": 1444701,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438712.817, "dur": 1.758, + "args": { + "External id": 1444702,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438720.525, "dur": 13.030, + "args": { + "External id": 1444703,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438738.531, "dur": 1.184, + "args": { + "External id": 1444704,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438744.124, "dur": 12.873, + "args": { + "External id": 1444705,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438761.615, "dur": 1.384, + "args": { + "External id": 1444706,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438767.194, "dur": 11.886, + "args": { + "External id": 1444707,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438783.313, "dur": 0.998, + "args": { + "External id": 1444708,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438788.391, "dur": 12.531, + "args": { + "External id": 1444709,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438804.959, "dur": 1.247, + "args": { + "External id": 1444710,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438810.535, "dur": 11.382, + "args": { + "External id": 1444711,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438826.092, "dur": 0.978, + "args": { + "External id": 1444712,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438831.144, "dur": 12.724, + "args": { + "External id": 1444713,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438847.931, "dur": 3.300, + "args": { + "External id": 1444714,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438857.609, "dur": 10.970, + "args": { + "External id": 1444715,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855438872.691, "dur": 0.949, + "args": { + "External id": 1444716,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855438877.687, "dur": 13.042, + "args": { + "External id": 1444717,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855439001.587, "dur": 2961.199, + "args": { + "External id": 1444718,"Record function id": 0, "Ev Idx": 10093 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413855439026.593, "dur": 1123.416, + "args": { + "External id": 1444719,"Record function id": 0, "Ev Idx": 10094 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413855439043.046, "dur": 376.560, + "args": { + "External id": 1444720,"Record function id": 0, "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439171.246, "dur": 5.396, + "args": { + "External id": 1444721,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439180.341, "dur": 0.761, + "args": { + "External id": 1444722,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439182.949, "dur": 0.977, + "args": { + "External id": 1444723,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439186.489, "dur": 1.493, + "args": { + "External id": 1444724,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439189.635, "dur": 1.231, + "args": { + "External id": 1444725,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439194.544, "dur": 1.333, + "args": { + "External id": 1444726,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439197.969, "dur": 3.196, + "args": { + "External id": 1444727,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439202.835, "dur": 2.226, + "args": { + "External id": 1444728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439206.511, "dur": 1.140, + "args": { + "External id": 1444729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855439211.728, "dur": 0.803, + "args": { + "External id": 1444730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855439231.932, "dur": 153.825, + "args": { + "External id": 1444731,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855439250.048, "dur": 130.728, + "args": { + "External id": 1444732,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855439265.821, "dur": 13.925, + "args": { + "External id": 1444733,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855439283.856, "dur": 67.897, + "args": { + "External id": 1444734,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855439286.869, "dur": 64.447, + "args": { + "External id": 1444735,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439290.935, "dur": 6.280, + "args": { + "External id": 1444736,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855439298.864, "dur": 51.819, + "args": { + "External id": 1444737,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 2338706, "tid": 2379422, + "ts": 6413855439511.877, "dur": 630.386, + "args": { + "External id": 1444738,"Record function id": 0, "Ev Idx": 10113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413855439529.969, "dur": 597.263, + "args": { + "External id": 1444739,"Record function id": 0, "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855439590.770, "dur": 4.927, + "args": { + "External id": 1444740,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855439610.689, "dur": 30.623, + "args": { + "External id": 1444741,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439615.808, "dur": 1.948, + "args": { + "External id": 1444742,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439619.556, "dur": 2.569, + "args": { + "External id": 1444743,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439624.140, "dur": 0.578, + "args": { + "External id": 1444744,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439626.511, "dur": 0.299, + "args": { + "External id": 1444745,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439628.446, "dur": 0.572, + "args": { + "External id": 1444746,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439630.557, "dur": 0.395, + "args": { + "External id": 1444747,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439632.572, "dur": 0.346, + "args": { + "External id": 1444748,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439634.599, "dur": 0.467, + "args": { + "External id": 1444749,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439637.406, "dur": 0.522, + "args": { + "External id": 1444750,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855439651.745, "dur": 40.180, + "args": { + "External id": 1444751,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855439721.612, "dur": 110.644, + "args": { + "External id": 1444752,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855439731.538, "dur": 5.278, + "args": { + "External id": 1444753,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855439742.295, "dur": 10.666, + "args": { + "External id": 1444754,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855439746.862, "dur": 5.673, + "args": { + "External id": 1444755,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439750.837, "dur": 0.460, + "args": { + "External id": 1444756,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855439759.571, "dur": 24.381, + "args": { + "External id": 1444757,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439761.836, "dur": 0.487, + "args": { + "External id": 1444758,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439763.897, "dur": 0.749, + "args": { + "External id": 1444759,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439766.316, "dur": 0.630, + "args": { + "External id": 1444760,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439768.926, "dur": 0.589, + "args": { + "External id": 1444761,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439770.785, "dur": 0.746, + "args": { + "External id": 1444762,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439773.289, "dur": 0.469, + "args": { + "External id": 1444763,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439775.365, "dur": 2.357, + "args": { + "External id": 1444764,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439778.906, "dur": 0.439, + "args": { + "External id": 1444765,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855439781.168, "dur": 0.377, + "args": { + "External id": 1444766,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855439794.329, "dur": 30.615, + "args": { + "External id": 1444767,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855439873.449, "dur": 138.787, + "args": { + "External id": 1444768,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855439897.605, "dur": 110.637, + "args": { + "External id": 1444769,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10144, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855439907.511, "dur": 95.503, + "args": { + "External id": 1444770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855440032.633, "dur": 2.188, + "args": { + "External id": 1444771,"Record function id": 0, "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": 10146, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855440159.243, "dur": 1781.251, + "args": { + "External id": 1444772,"Sequence number": 15348907, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10147 + } + }, + { + "ph": "f", "id": 428, "pid": 2338706, "tid": 2379422, "ts": 6413855440159.243, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440276.185, "dur": 112.685, + "args": { + "External id": 1444773,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855440432.627, "dur": 42.362, + "args": { + "External id": 1444774,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440500.712, "dur": 51.641, + "args": { + "External id": 1444775,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440562.513, "dur": 31.892, + "args": { + "External id": 1444776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440600.774, "dur": 31.548, + "args": { + "External id": 1444777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440640.899, "dur": 29.075, + "args": { + "External id": 1444778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440676.578, "dur": 27.723, + "args": { + "External id": 1444779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855440731.117, "dur": 24.042, + "args": { + "External id": 1444780,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855440775.477, "dur": 28.765, + "args": { + "External id": 1444781,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855440826.788, "dur": 19.208, + "args": { + "External id": 1444782,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855440858.639, "dur": 15.140, + "args": { + "External id": 1444783,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440884.671, "dur": 36.070, + "args": { + "External id": 1444784,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855440924.696, "dur": 34.267, + "args": { + "External id": 1444785,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855441024.841, "dur": 297.430, + "args": { + "External id": 1444786,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855441145.271, "dur": 8.719, + "args": { + "External id": 1444787,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855441156.642, "dur": 3.854, + "args": { + "External id": 1444788,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855441162.002, "dur": 5.163, + "args": { + "External id": 1444789,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855441168.642, "dur": 2.779, + "args": { + "External id": 1444790,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855441219.162, "dur": 5.478, + "args": { + "External id": 1444791,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855441221.570, "dur": 2.914, + "args": { + "External id": 1444792,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855441226.513, "dur": 32.518, + "args": { + "External id": 1444793,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855441232.287, "dur": 1.903, + "args": { + "External id": 1444794,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855441260.502, "dur": 1.788, + "args": { + "External id": 1444795,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855441261.479, "dur": 0.734, + "args": { + "External id": 1444796,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855441263.325, "dur": 15.106, + "args": { + "External id": 1444797,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855441265.526, "dur": 0.611, + "args": { + "External id": 1444798,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855441361.388, "dur": 27.437, + "args": { + "External id": 1444799,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855441407.026, "dur": 17.426, + "args": { + "External id": 1444800,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855441434.334, "dur": 51.835, + "args": { + "External id": 1444801,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855441493.827, "dur": 41.197, + "args": { + "External id": 1444802,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855441546.360, "dur": 36.315, + "args": { + "External id": 1444803,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855441597.376, "dur": 38.030, + "args": { + "External id": 1444804,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855441643.603, "dur": 28.328, + "args": { + "External id": 1444805,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855441678.887, "dur": 30.987, + "args": { + "External id": 1444806,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855441730.644, "dur": 27.922, + "args": { + "External id": 1444807,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855441778.301, "dur": 27.228, + "args": { + "External id": 1444808,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855441824.231, "dur": 20.540, + "args": { + "External id": 1444809,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855441859.045, "dur": 15.849, + "args": { + "External id": 1444810,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855441887.480, "dur": 18.685, + "args": { + "External id": 1444811,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442004.412, "dur": 19.665, + "args": { + "External id": 1444812,"Record function id": 0, "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442009.612, "dur": 13.080, + "args": { + "External id": 1444813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442014.559, "dur": 6.918, + "args": { + "External id": 1444814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442016.516, "dur": 4.683, + "args": { + "External id": 1444815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442030.071, "dur": 7.312, + "args": { + "External id": 1444816,"Record function id": 0, "Ev Idx": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442032.019, "dur": 4.877, + "args": { + "External id": 1444817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442033.162, "dur": 2.876, + "args": { + "External id": 1444818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442034.445, "dur": 1.449, + "args": { + "External id": 1444819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442040.773, "dur": 6.111, + "args": { + "External id": 1444820,"Record function id": 0, "Ev Idx": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442042.679, "dur": 3.682, + "args": { + "External id": 1444821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442043.416, "dur": 2.493, + "args": { + "External id": 1444822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442044.705, "dur": 1.134, + "args": { + "External id": 1444823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442050.126, "dur": 44.326, + "args": { + "External id": 1444824,"Record function id": 0, "Ev Idx": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442051.540, "dur": 41.605, + "args": { + "External id": 1444825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442052.092, "dur": 39.918, + "args": { + "External id": 1444826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442089.540, "dur": 2.205, + "args": { + "External id": 1444827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442099.820, "dur": 6.697, + "args": { + "External id": 1444828,"Record function id": 0, "Ev Idx": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442101.821, "dur": 4.246, + "args": { + "External id": 1444829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442102.734, "dur": 2.446, + "args": { + "External id": 1444830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442103.768, "dur": 1.333, + "args": { + "External id": 1444831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442109.698, "dur": 9.370, + "args": { + "External id": 1444832,"Record function id": 0, "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442111.563, "dur": 7.049, + "args": { + "External id": 1444833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442112.652, "dur": 5.487, + "args": { + "External id": 1444834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442114.188, "dur": 3.861, + "args": { + "External id": 1444835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442122.429, "dur": 5.884, + "args": { + "External id": 1444836,"Record function id": 0, "Ev Idx": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442124.387, "dur": 3.500, + "args": { + "External id": 1444837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442124.941, "dur": 2.479, + "args": { + "External id": 1444838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442125.900, "dur": 1.438, + "args": { + "External id": 1444839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442131.534, "dur": 5.942, + "args": { + "External id": 1444840,"Record function id": 0, "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442133.645, "dur": 3.424, + "args": { + "External id": 1444841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442134.191, "dur": 2.246, + "args": { + "External id": 1444842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442135.261, "dur": 1.092, + "args": { + "External id": 1444843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442140.704, "dur": 5.982, + "args": { + "External id": 1444844,"Record function id": 0, "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855442142.852, "dur": 3.355, + "args": { + "External id": 1444845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442143.470, "dur": 1.984, + "args": { + "External id": 1444846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855442144.268, "dur": 1.086, + "args": { + "External id": 1444847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855442151.039, "dur": 65433.855, + "args": { + "External id": 1444848,"Record function id": 0, "Sequence number": 15348906, "Fwd thread id": 1, "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855442152.756, "dur": 65422.349, + "args": { + "External id": 1444849,"Sequence number": 15348906, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10224 + } + }, + { + "ph": "f", "id": 429, "pid": 2338706, "tid": 2379422, "ts": 6413855442152.756, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413855442187.302, "dur": 42.001, + "args": { + "External id": 1444850,"Record function id": 0, "Ev Idx": 10225 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413855442237.252, "dur": 71.877, + "args": { + "External id": 1444851,"Record function id": 0, "Ev Idx": 10226 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 2338706, "tid": 2379422, + "ts": 6413855442315.173, "dur": 65252.313, + "args": { + "External id": 1444852,"Record function id": 0, "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855442409.828, "dur": 7.673, + "args": { + "External id": 1444853,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855442427.356, "dur": 4.561, + "args": { + "External id": 1444854,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855442446.359, "dur": 64029.061, + "args": { + "External id": 1444855,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855442460.797, "dur": 64001.508, + "args": { + "External id": 1444856,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855442579.251, "dur": 18.433, + "args": { + "External id": 1444857,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855442617.697, "dur": 63796.981, + "args": { + "External id": 1444858,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855442620.692, "dur": 63792.858, + "args": { + "External id": 1444859,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855442625.801, "dur": 8.091, + "args": { + "External id": 1444860,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855442636.440, "dur": 63772.078, + "args": { + "External id": 1444861,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855506588.361, "dur": 13.674, + "args": { + "External id": 1444862,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855506591.854, "dur": 9.734, + "args": { + "External id": 1444863,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855506633.080, "dur": 526.334, + "args": { + "External id": 1444864,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855506719.571, "dur": 433.662, + "args": { + "External id": 1444865,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10240, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855506732.469, "dur": 414.486, + "args": { + "External id": 1444866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855507185.867, "dur": 2.532, + "args": { + "External id": 1444867,"Record function id": 0, "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": 10242, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507259.087, "dur": 8.668, + "args": { + "External id": 1444868,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507280.838, "dur": 37.604, + "args": { + "External id": 1444869,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507328.810, "dur": 1.454, + "args": { + "External id": 1444870,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507336.884, "dur": 13.072, + "args": { + "External id": 1444871,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507355.861, "dur": 0.972, + "args": { + "External id": 1444872,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507361.085, "dur": 13.076, + "args": { + "External id": 1444873,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507379.511, "dur": 1.236, + "args": { + "External id": 1444874,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507384.967, "dur": 11.289, + "args": { + "External id": 1444875,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507400.488, "dur": 0.900, + "args": { + "External id": 1444876,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507405.702, "dur": 13.476, + "args": { + "External id": 1444877,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507424.060, "dur": 1.301, + "args": { + "External id": 1444878,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507429.380, "dur": 11.636, + "args": { + "External id": 1444879,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507445.792, "dur": 0.969, + "args": { + "External id": 1444880,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507451.012, "dur": 12.608, + "args": { + "External id": 1444881,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507467.861, "dur": 0.661, + "args": { + "External id": 1444882,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507472.518, "dur": 11.499, + "args": { + "External id": 1444883,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507488.236, "dur": 2.945, + "args": { + "External id": 1444884,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507495.082, "dur": 12.670, + "args": { + "External id": 1444885,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855507599.803, "dur": 3027.111, + "args": { + "External id": 1444886,"Record function id": 0, "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413855507620.830, "dur": 1135.451, + "args": { + "External id": 1444887,"Record function id": 0, "Ev Idx": 10262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413855507637.252, "dur": 316.975, + "args": { + "External id": 1444888,"Record function id": 0, "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507727.648, "dur": 4.439, + "args": { + "External id": 1444889,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507736.073, "dur": 0.801, + "args": { + "External id": 1444890,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507738.755, "dur": 1.482, + "args": { + "External id": 1444891,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507742.453, "dur": 1.191, + "args": { + "External id": 1444892,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507747.204, "dur": 0.924, + "args": { + "External id": 1444893,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507749.482, "dur": 0.933, + "args": { + "External id": 1444894,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507752.017, "dur": 1.163, + "args": { + "External id": 1444895,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507754.345, "dur": 3.987, + "args": { + "External id": 1444896,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507762.038, "dur": 0.647, + "args": { + "External id": 1444897,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855507764.055, "dur": 0.644, + "args": { + "External id": 1444898,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855507782.938, "dur": 143.542, + "args": { + "External id": 1444899,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855507800.092, "dur": 121.948, + "args": { + "External id": 1444900,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855507815.110, "dur": 13.375, + "args": { + "External id": 1444901,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855507832.271, "dur": 62.735, + "args": { + "External id": 1444902,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855507835.285, "dur": 59.365, + "args": { + "External id": 1444903,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855507839.067, "dur": 6.144, + "args": { + "External id": 1444904,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855507847.118, "dur": 46.770, + "args": { + "External id": 1444905,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10280 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 2338706, "tid": 2379422, + "ts": 6413855508108.926, "dur": 639.564, + "args": { + "External id": 1444906,"Record function id": 0, "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413855508127.457, "dur": 607.315, + "args": { + "External id": 1444907,"Record function id": 0, "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855508199.597, "dur": 6.689, + "args": { + "External id": 1444908,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855508223.115, "dur": 31.241, + "args": { + "External id": 1444909,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508228.557, "dur": 1.868, + "args": { + "External id": 1444910,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508232.577, "dur": 0.739, + "args": { + "External id": 1444911,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508235.322, "dur": 2.584, + "args": { + "External id": 1444912,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508239.145, "dur": 0.842, + "args": { + "External id": 1444913,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508241.680, "dur": 0.438, + "args": { + "External id": 1444914,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508244.069, "dur": 0.573, + "args": { + "External id": 1444915,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508245.670, "dur": 0.614, + "args": { + "External id": 1444916,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508247.954, "dur": 0.369, + "args": { + "External id": 1444917,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508249.934, "dur": 0.422, + "args": { + "External id": 1444918,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855508303.529, "dur": 45.459, + "args": { + "External id": 1444919,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855508382.502, "dur": 108.666, + "args": { + "External id": 1444920,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855508393.273, "dur": 3.895, + "args": { + "External id": 1444921,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855508402.282, "dur": 13.175, + "args": { + "External id": 1444922,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855508406.773, "dur": 8.250, + "args": { + "External id": 1444923,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508410.561, "dur": 3.163, + "args": { + "External id": 1444924,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855508421.903, "dur": 23.793, + "args": { + "External id": 1444925,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508423.628, "dur": 0.521, + "args": { + "External id": 1444926,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508425.563, "dur": 0.723, + "args": { + "External id": 1444927,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508428.134, "dur": 0.437, + "args": { + "External id": 1444928,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508430.022, "dur": 0.454, + "args": { + "External id": 1444929,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508431.983, "dur": 0.652, + "args": { + "External id": 1444930,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508434.244, "dur": 0.367, + "args": { + "External id": 1444931,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508436.503, "dur": 0.365, + "args": { + "External id": 1444932,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508438.365, "dur": 2.591, + "args": { + "External id": 1444933,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855508442.531, "dur": 0.563, + "args": { + "External id": 1444934,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855508455.927, "dur": 27.644, + "args": { + "External id": 1444935,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855508539.439, "dur": 123.768, + "args": { + "External id": 1444936,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855508568.562, "dur": 91.014, + "args": { + "External id": 1444937,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10312, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855508578.801, "dur": 76.611, + "args": { + "External id": 1444938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855508681.446, "dur": 1.747, + "args": { + "External id": 1444939,"Record function id": 0, "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": 10314, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855508764.688, "dur": 1838.953, + "args": { + "External id": 1444940,"Sequence number": 15348905, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10315 + } + }, + { + "ph": "f", "id": 430, "pid": 2338706, "tid": 2379422, "ts": 6413855508764.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855508878.492, "dur": 127.238, + "args": { + "External id": 1444941,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855509089.559, "dur": 47.708, + "args": { + "External id": 1444942,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509159.887, "dur": 59.840, + "args": { + "External id": 1444943,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509230.641, "dur": 32.725, + "args": { + "External id": 1444944,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509269.541, "dur": 33.399, + "args": { + "External id": 1444945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509309.121, "dur": 27.687, + "args": { + "External id": 1444946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509345.578, "dur": 28.642, + "args": { + "External id": 1444947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855509403.204, "dur": 23.979, + "args": { + "External id": 1444948,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855509447.286, "dur": 30.192, + "args": { + "External id": 1444949,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855509501.112, "dur": 19.354, + "args": { + "External id": 1444950,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855509534.854, "dur": 14.007, + "args": { + "External id": 1444951,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509560.266, "dur": 36.877, + "args": { + "External id": 1444952,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855509600.902, "dur": 33.937, + "args": { + "External id": 1444953,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855509668.310, "dur": 253.375, + "args": { + "External id": 1444954,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855509751.037, "dur": 6.131, + "args": { + "External id": 1444955,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855509759.119, "dur": 3.376, + "args": { + "External id": 1444956,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855509763.995, "dur": 2.664, + "args": { + "External id": 1444957,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855509767.931, "dur": 4.570, + "args": { + "External id": 1444958,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855509817.991, "dur": 5.246, + "args": { + "External id": 1444959,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855509820.293, "dur": 2.774, + "args": { + "External id": 1444960,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855509825.181, "dur": 31.107, + "args": { + "External id": 1444961,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855509830.723, "dur": 1.725, + "args": { + "External id": 1444962,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855509857.947, "dur": 1.742, + "args": { + "External id": 1444963,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855509858.802, "dur": 0.800, + "args": { + "External id": 1444964,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855509860.878, "dur": 17.388, + "args": { + "External id": 1444965,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855509862.797, "dur": 0.542, + "args": { + "External id": 1444966,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855509955.799, "dur": 43.921, + "args": { + "External id": 1444967,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855510019.763, "dur": 18.330, + "args": { + "External id": 1444968,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855510047.174, "dur": 99.664, + "args": { + "External id": 1444969,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855510166.472, "dur": 45.636, + "args": { + "External id": 1444970,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855510227.333, "dur": 23.532, + "args": { + "External id": 1444971,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855510257.753, "dur": 34.367, + "args": { + "External id": 1444972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855510300.162, "dur": 31.121, + "args": { + "External id": 1444973,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855510339.664, "dur": 30.835, + "args": { + "External id": 1444974,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855510391.975, "dur": 28.589, + "args": { + "External id": 1444975,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855510437.891, "dur": 29.257, + "args": { + "External id": 1444976,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855510482.269, "dur": 20.491, + "args": { + "External id": 1444977,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855510517.070, "dur": 16.543, + "args": { + "External id": 1444978,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855510551.587, "dur": 18.040, + "args": { + "External id": 1444979,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510650.500, "dur": 16.587, + "args": { + "External id": 1444980,"Record function id": 0, "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510654.118, "dur": 11.874, + "args": { + "External id": 1444981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510658.834, "dur": 6.035, + "args": { + "External id": 1444982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510660.654, "dur": 4.103, + "args": { + "External id": 1444983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510671.083, "dur": 5.591, + "args": { + "External id": 1444984,"Record function id": 0, "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510672.450, "dur": 3.634, + "args": { + "External id": 1444985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510673.059, "dur": 2.471, + "args": { + "External id": 1444986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510674.168, "dur": 1.258, + "args": { + "External id": 1444987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510679.929, "dur": 5.428, + "args": { + "External id": 1444988,"Record function id": 0, "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510681.731, "dur": 3.210, + "args": { + "External id": 1444989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510682.180, "dur": 2.347, + "args": { + "External id": 1444990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510683.428, "dur": 1.022, + "args": { + "External id": 1444991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510688.584, "dur": 4.677, + "args": { + "External id": 1444992,"Record function id": 0, "Ev Idx": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510689.704, "dur": 3.127, + "args": { + "External id": 1444993,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510690.146, "dur": 2.123, + "args": { + "External id": 1444994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510691.041, "dur": 1.142, + "args": { + "External id": 1444995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510696.336, "dur": 7.926, + "args": { + "External id": 1444996,"Record function id": 0, "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510697.941, "dur": 5.870, + "args": { + "External id": 1444997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510698.411, "dur": 4.740, + "args": { + "External id": 1444998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510699.267, "dur": 3.797, + "args": { + "External id": 1444999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510707.371, "dur": 5.030, + "args": { + "External id": 1445000,"Record function id": 0, "Ev Idx": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510708.800, "dur": 3.167, + "args": { + "External id": 1445001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510709.269, "dur": 2.269, + "args": { + "External id": 1445002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510710.109, "dur": 1.358, + "args": { + "External id": 1445003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510715.587, "dur": 5.579, + "args": { + "External id": 1445004,"Record function id": 0, "Ev Idx": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510716.849, "dur": 3.902, + "args": { + "External id": 1445005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510717.415, "dur": 2.670, + "args": { + "External id": 1445006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510718.625, "dur": 1.389, + "args": { + "External id": 1445007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510724.209, "dur": 5.607, + "args": { + "External id": 1445008,"Record function id": 0, "Ev Idx": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510725.567, "dur": 3.804, + "args": { + "External id": 1445009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510726.230, "dur": 2.348, + "args": { + "External id": 1445010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510727.125, "dur": 1.378, + "args": { + "External id": 1445011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510733.479, "dur": 4.979, + "args": { + "External id": 1445012,"Record function id": 0, "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855510734.625, "dur": 3.419, + "args": { + "External id": 1445013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510735.193, "dur": 2.189, + "args": { + "External id": 1445014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855510736.104, "dur": 1.197, + "args": { + "External id": 1445015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855510743.088, "dur": 63425.070, + "args": { + "External id": 1445016,"Record function id": 0, "Sequence number": 15348904, "Fwd thread id": 1, "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855510744.548, "dur": 63412.637, + "args": { + "External id": 1445017,"Sequence number": 15348904, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10392 + } + }, + { + "ph": "f", "id": 431, "pid": 2338706, "tid": 2379422, "ts": 6413855510744.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413855510774.911, "dur": 39.272, + "args": { + "External id": 1445018,"Record function id": 0, "Ev Idx": 10393 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413855510822.219, "dur": 70.200, + "args": { + "External id": 1445019,"Record function id": 0, "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 2338706, "tid": 2379422, + "ts": 6413855510899.354, "dur": 63249.054, + "args": { + "External id": 1445020,"Record function id": 0, "Ev Idx": 10395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855511008.179, "dur": 8.230, + "args": { + "External id": 1445021,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855511028.158, "dur": 5.236, + "args": { + "External id": 1445022,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855511048.836, "dur": 62128.423, + "args": { + "External id": 1445023,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855511098.968, "dur": 62064.888, + "args": { + "External id": 1445024,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855511270.503, "dur": 20.312, + "args": { + "External id": 1445025,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855511314.068, "dur": 61801.354, + "args": { + "External id": 1445026,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855511317.353, "dur": 61797.126, + "args": { + "External id": 1445027,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855511322.012, "dur": 10.770, + "args": { + "External id": 1445028,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855511335.371, "dur": 61774.210, + "args": { + "External id": 1445029,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855573290.161, "dur": 12.307, + "args": { + "External id": 1445030,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855573293.613, "dur": 8.456, + "args": { + "External id": 1445031,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573334.043, "dur": 381.950, + "args": { + "External id": 1445032,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855573365.935, "dur": 344.913, + "args": { + "External id": 1445033,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10408, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855573378.238, "dur": 325.638, + "args": { + "External id": 1445034,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855573735.600, "dur": 2.222, + "args": { + "External id": 1445035,"Record function id": 0, "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": 10410, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573794.149, "dur": 6.555, + "args": { + "External id": 1445036,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573813.314, "dur": 34.404, + "args": { + "External id": 1445037,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573857.852, "dur": 1.443, + "args": { + "External id": 1445038,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573865.732, "dur": 12.904, + "args": { + "External id": 1445039,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573883.527, "dur": 2.959, + "args": { + "External id": 1445040,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573891.320, "dur": 12.407, + "args": { + "External id": 1445041,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573908.716, "dur": 0.731, + "args": { + "External id": 1445042,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573913.905, "dur": 10.681, + "args": { + "External id": 1445043,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573928.867, "dur": 0.878, + "args": { + "External id": 1445044,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573934.254, "dur": 10.540, + "args": { + "External id": 1445045,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573948.957, "dur": 1.029, + "args": { + "External id": 1445046,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573954.581, "dur": 10.381, + "args": { + "External id": 1445047,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855573969.454, "dur": 1.126, + "args": { + "External id": 1445048,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855573974.858, "dur": 29.760, + "args": { + "External id": 1445049,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574014.302, "dur": 1.689, + "args": { + "External id": 1445050,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855574020.702, "dur": 11.071, + "args": { + "External id": 1445051,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574035.973, "dur": 1.024, + "args": { + "External id": 1445052,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855574041.683, "dur": 10.579, + "args": { + "External id": 1445053,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855574186.309, "dur": 2967.527, + "args": { + "External id": 1445054,"Record function id": 0, "Ev Idx": 10429 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413855574207.960, "dur": 1064.630, + "args": { + "External id": 1445055,"Record function id": 0, "Ev Idx": 10430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413855574224.834, "dur": 327.346, + "args": { + "External id": 1445056,"Record function id": 0, "Ev Idx": 10431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574315.618, "dur": 5.196, + "args": { + "External id": 1445057,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574324.145, "dur": 3.809, + "args": { + "External id": 1445058,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574330.515, "dur": 1.173, + "args": { + "External id": 1445059,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574333.609, "dur": 0.926, + "args": { + "External id": 1445060,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574336.420, "dur": 0.859, + "args": { + "External id": 1445061,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574338.568, "dur": 1.108, + "args": { + "External id": 1445062,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574341.058, "dur": 0.806, + "args": { + "External id": 1445063,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574345.364, "dur": 1.981, + "args": { + "External id": 1445064,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574348.657, "dur": 0.912, + "args": { + "External id": 1445065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855574350.826, "dur": 2.391, + "args": { + "External id": 1445066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855574371.275, "dur": 152.801, + "args": { + "External id": 1445067,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855574388.251, "dur": 130.788, + "args": { + "External id": 1445068,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855574405.527, "dur": 15.895, + "args": { + "External id": 1445069,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855574425.471, "dur": 64.677, + "args": { + "External id": 1445070,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855574428.480, "dur": 61.293, + "args": { + "External id": 1445071,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574432.579, "dur": 5.856, + "args": { + "External id": 1445072,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855574440.342, "dur": 48.568, + "args": { + "External id": 1445073,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10448 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 2338706, "tid": 2379422, + "ts": 6413855574637.250, "dur": 627.849, + "args": { + "External id": 1445074,"Record function id": 0, "Ev Idx": 10449 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413855574653.014, "dur": 599.352, + "args": { + "External id": 1445075,"Record function id": 0, "Ev Idx": 10450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855574716.850, "dur": 4.691, + "args": { + "External id": 1445076,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855574736.183, "dur": 29.580, + "args": { + "External id": 1445077,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574741.327, "dur": 1.546, + "args": { + "External id": 1445078,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574745.375, "dur": 0.525, + "args": { + "External id": 1445079,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574747.263, "dur": 0.511, + "args": { + "External id": 1445080,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574749.759, "dur": 0.506, + "args": { + "External id": 1445081,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574752.003, "dur": 2.616, + "args": { + "External id": 1445082,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574755.829, "dur": 0.502, + "args": { + "External id": 1445083,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574758.127, "dur": 0.473, + "args": { + "External id": 1445084,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574760.155, "dur": 0.500, + "args": { + "External id": 1445085,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574761.882, "dur": 0.469, + "args": { + "External id": 1445086,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855574776.449, "dur": 39.534, + "args": { + "External id": 1445087,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855574845.521, "dur": 106.785, + "args": { + "External id": 1445088,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855574855.362, "dur": 3.054, + "args": { + "External id": 1445089,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855574863.522, "dur": 11.012, + "args": { + "External id": 1445090,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855574868.262, "dur": 5.839, + "args": { + "External id": 1445091,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574872.306, "dur": 0.621, + "args": { + "External id": 1445092,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855574881.012, "dur": 22.622, + "args": { + "External id": 1445093,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574883.032, "dur": 0.473, + "args": { + "External id": 1445094,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574884.739, "dur": 2.836, + "args": { + "External id": 1445095,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574889.388, "dur": 0.604, + "args": { + "External id": 1445096,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574891.531, "dur": 0.598, + "args": { + "External id": 1445097,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574893.123, "dur": 0.634, + "args": { + "External id": 1445098,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574895.360, "dur": 0.495, + "args": { + "External id": 1445099,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574897.504, "dur": 0.297, + "args": { + "External id": 1445100,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574898.813, "dur": 0.423, + "args": { + "External id": 1445101,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855574900.839, "dur": 0.462, + "args": { + "External id": 1445102,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855574913.411, "dur": 29.712, + "args": { + "External id": 1445103,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855575018.379, "dur": 157.926, + "args": { + "External id": 1445104,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855575044.944, "dur": 127.405, + "args": { + "External id": 1445105,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10480, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855575088.973, "dur": 79.280, + "args": { + "External id": 1445106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855575193.352, "dur": 2.258, + "args": { + "External id": 1445107,"Record function id": 0, "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": 10482, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855575280.172, "dur": 1846.077, + "args": { + "External id": 1445108,"Sequence number": 15348903, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10483 + } + }, + { + "ph": "f", "id": 432, "pid": 2338706, "tid": 2379422, "ts": 6413855575280.172, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855575395.324, "dur": 105.713, + "args": { + "External id": 1445109,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855575546.333, "dur": 43.541, + "args": { + "External id": 1445110,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855575609.529, "dur": 50.881, + "args": { + "External id": 1445111,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855575669.976, "dur": 31.558, + "args": { + "External id": 1445112,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855575708.030, "dur": 32.502, + "args": { + "External id": 1445113,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855575746.873, "dur": 26.738, + "args": { + "External id": 1445114,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855575782.159, "dur": 28.952, + "args": { + "External id": 1445115,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855575837.236, "dur": 26.100, + "args": { + "External id": 1445116,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855575881.711, "dur": 28.956, + "args": { + "External id": 1445117,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855575932.710, "dur": 19.968, + "args": { + "External id": 1445118,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855575967.876, "dur": 33.367, + "args": { + "External id": 1445119,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576033.791, "dur": 80.548, + "args": { + "External id": 1445120,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576121.485, "dur": 36.277, + "args": { + "External id": 1445121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855576191.466, "dur": 257.510, + "args": { + "External id": 1445122,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855576277.465, "dur": 7.287, + "args": { + "External id": 1445123,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855576286.901, "dur": 2.773, + "args": { + "External id": 1445124,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855576290.928, "dur": 2.344, + "args": { + "External id": 1445125,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855576294.259, "dur": 5.233, + "args": { + "External id": 1445126,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855576345.697, "dur": 5.512, + "args": { + "External id": 1445127,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855576347.894, "dur": 3.140, + "args": { + "External id": 1445128,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855576353.036, "dur": 32.163, + "args": { + "External id": 1445129,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855576358.921, "dur": 1.954, + "args": { + "External id": 1445130,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855576386.716, "dur": 2.007, + "args": { + "External id": 1445131,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855576387.901, "dur": 0.735, + "args": { + "External id": 1445132,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855576390.015, "dur": 16.168, + "args": { + "External id": 1445133,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855576391.843, "dur": 0.626, + "args": { + "External id": 1445134,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855576486.601, "dur": 37.036, + "args": { + "External id": 1445135,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855576539.757, "dur": 19.895, + "args": { + "External id": 1445136,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576568.572, "dur": 41.686, + "args": { + "External id": 1445137,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576617.118, "dur": 39.013, + "args": { + "External id": 1445138,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576666.988, "dur": 22.255, + "args": { + "External id": 1445139,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576695.746, "dur": 32.286, + "args": { + "External id": 1445140,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576735.787, "dur": 29.152, + "args": { + "External id": 1445141,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855576772.514, "dur": 49.866, + "args": { + "External id": 1445142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855576847.647, "dur": 25.293, + "args": { + "External id": 1445143,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855576889.502, "dur": 29.275, + "args": { + "External id": 1445144,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855576932.803, "dur": 19.285, + "args": { + "External id": 1445145,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855576970.588, "dur": 34.976, + "args": { + "External id": 1445146,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855577022.840, "dur": 20.526, + "args": { + "External id": 1445147,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577178.209, "dur": 17.578, + "args": { + "External id": 1445148,"Record function id": 0, "Ev Idx": 10523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577182.936, "dur": 11.860, + "args": { + "External id": 1445149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577187.589, "dur": 6.303, + "args": { + "External id": 1445150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577189.550, "dur": 4.226, + "args": { + "External id": 1445151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577199.610, "dur": 7.530, + "args": { + "External id": 1445152,"Record function id": 0, "Ev Idx": 10527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577201.684, "dur": 4.943, + "args": { + "External id": 1445153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577203.001, "dur": 2.945, + "args": { + "External id": 1445154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577204.460, "dur": 1.385, + "args": { + "External id": 1445155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577210.343, "dur": 5.853, + "args": { + "External id": 1445156,"Record function id": 0, "Ev Idx": 10531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577212.247, "dur": 3.525, + "args": { + "External id": 1445157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577212.878, "dur": 2.359, + "args": { + "External id": 1445158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577214.004, "dur": 1.151, + "args": { + "External id": 1445159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577219.357, "dur": 5.180, + "args": { + "External id": 1445160,"Record function id": 0, "Ev Idx": 10535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577220.679, "dur": 3.436, + "args": { + "External id": 1445161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577221.280, "dur": 2.374, + "args": { + "External id": 1445162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577222.161, "dur": 1.410, + "args": { + "External id": 1445163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577227.611, "dur": 8.348, + "args": { + "External id": 1445164,"Record function id": 0, "Ev Idx": 10539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577229.548, "dur": 5.960, + "args": { + "External id": 1445165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577230.226, "dur": 4.704, + "args": { + "External id": 1445166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577231.469, "dur": 3.376, + "args": { + "External id": 1445167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577239.064, "dur": 5.582, + "args": { + "External id": 1445168,"Record function id": 0, "Ev Idx": 10543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577240.724, "dur": 3.487, + "args": { + "External id": 1445169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577241.336, "dur": 2.277, + "args": { + "External id": 1445170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577242.413, "dur": 1.129, + "args": { + "External id": 1445171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577247.814, "dur": 5.435, + "args": { + "External id": 1445172,"Record function id": 0, "Ev Idx": 10547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577249.459, "dur": 3.386, + "args": { + "External id": 1445173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577249.871, "dur": 2.571, + "args": { + "External id": 1445174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577250.784, "dur": 1.585, + "args": { + "External id": 1445175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577256.310, "dur": 6.660, + "args": { + "External id": 1445176,"Record function id": 0, "Ev Idx": 10551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577258.722, "dur": 3.858, + "args": { + "External id": 1445177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577259.566, "dur": 2.391, + "args": { + "External id": 1445178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577260.661, "dur": 1.205, + "args": { + "External id": 1445179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577266.343, "dur": 4.151, + "args": { + "External id": 1445180,"Record function id": 0, "Ev Idx": 10555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855577267.758, "dur": 2.317, + "args": { + "External id": 1445181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577268.244, "dur": 1.412, + "args": { + "External id": 1445182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855577268.571, "dur": 0.989, + "args": { + "External id": 1445183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855577274.642, "dur": 64315.255, + "args": { + "External id": 1445184,"Record function id": 0, "Sequence number": 15348902, "Fwd thread id": 1, "Ev Idx": 10559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855577276.466, "dur": 64303.319, + "args": { + "External id": 1445185,"Sequence number": 15348902, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10560 + } + }, + { + "ph": "f", "id": 433, "pid": 2338706, "tid": 2379422, "ts": 6413855577276.466, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413855577308.747, "dur": 41.771, + "args": { + "External id": 1445186,"Record function id": 0, "Ev Idx": 10561 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413855577358.115, "dur": 72.232, + "args": { + "External id": 1445187,"Record function id": 0, "Ev Idx": 10562 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 2338706, "tid": 2379422, + "ts": 6413855577439.445, "dur": 64131.178, + "args": { + "External id": 1445188,"Record function id": 0, "Ev Idx": 10563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855577532.799, "dur": 7.130, + "args": { + "External id": 1445189,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855577549.789, "dur": 4.636, + "args": { + "External id": 1445190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855577569.000, "dur": 62965.428, + "args": { + "External id": 1445191,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855577583.137, "dur": 62938.499, + "args": { + "External id": 1445192,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855577696.445, "dur": 18.909, + "args": { + "External id": 1445193,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855577735.141, "dur": 62740.484, + "args": { + "External id": 1445194,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855577740.565, "dur": 62733.968, + "args": { + "External id": 1445195,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855577745.267, "dur": 9.087, + "args": { + "External id": 1445196,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855577756.131, "dur": 62713.377, + "args": { + "External id": 1445197,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855640649.617, "dur": 12.489, + "args": { + "External id": 1445198,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855640653.346, "dur": 8.418, + "args": { + "External id": 1445199,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855640693.987, "dur": 482.600, + "args": { + "External id": 1445200,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855640729.298, "dur": 441.255, + "args": { + "External id": 1445201,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10576, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855640741.560, "dur": 422.762, + "args": { + "External id": 1445202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855641203.276, "dur": 2.407, + "args": { + "External id": 1445203,"Record function id": 0, "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": 10578, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641275.811, "dur": 7.099, + "args": { + "External id": 1445204,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641296.039, "dur": 35.695, + "args": { + "External id": 1445205,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641342.132, "dur": 3.889, + "args": { + "External id": 1445206,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641352.048, "dur": 11.746, + "args": { + "External id": 1445207,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641369.479, "dur": 1.109, + "args": { + "External id": 1445208,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641375.201, "dur": 10.825, + "args": { + "External id": 1445209,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641391.636, "dur": 0.966, + "args": { + "External id": 1445210,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641396.943, "dur": 10.003, + "args": { + "External id": 1445211,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641411.254, "dur": 0.978, + "args": { + "External id": 1445212,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641416.530, "dur": 10.939, + "args": { + "External id": 1445213,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641431.688, "dur": 1.260, + "args": { + "External id": 1445214,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641437.241, "dur": 10.104, + "args": { + "External id": 1445215,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641453.875, "dur": 0.965, + "args": { + "External id": 1445216,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641459.116, "dur": 10.124, + "args": { + "External id": 1445217,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641473.806, "dur": 0.967, + "args": { + "External id": 1445218,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641479.142, "dur": 10.113, + "args": { + "External id": 1445219,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641493.577, "dur": 1.031, + "args": { + "External id": 1445220,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641498.355, "dur": 10.633, + "args": { + "External id": 1445221,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855641605.260, "dur": 3023.408, + "args": { + "External id": 1445222,"Record function id": 0, "Ev Idx": 10597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413855641626.988, "dur": 1093.092, + "args": { + "External id": 1445223,"Record function id": 0, "Ev Idx": 10598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413855641642.935, "dur": 316.949, + "args": { + "External id": 1445224,"Record function id": 0, "Ev Idx": 10599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641732.615, "dur": 6.628, + "args": { + "External id": 1445225,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641742.776, "dur": 1.112, + "args": { + "External id": 1445226,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641745.777, "dur": 0.745, + "args": { + "External id": 1445227,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641750.470, "dur": 0.683, + "args": { + "External id": 1445228,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641752.808, "dur": 0.823, + "args": { + "External id": 1445229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641754.943, "dur": 0.888, + "args": { + "External id": 1445230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641757.506, "dur": 0.702, + "args": { + "External id": 1445231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641761.218, "dur": 1.719, + "args": { + "External id": 1445232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641764.595, "dur": 2.521, + "args": { + "External id": 1445233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855641768.812, "dur": 0.679, + "args": { + "External id": 1445234,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855641787.349, "dur": 145.005, + "args": { + "External id": 1445235,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855641804.028, "dur": 123.894, + "args": { + "External id": 1445236,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855641819.204, "dur": 15.362, + "args": { + "External id": 1445237,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855641838.101, "dur": 62.765, + "args": { + "External id": 1445238,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855641843.343, "dur": 57.133, + "args": { + "External id": 1445239,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855641847.061, "dur": 5.354, + "args": { + "External id": 1445240,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855641854.129, "dur": 45.853, + "args": { + "External id": 1445241,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 2338706, "tid": 2379422, + "ts": 6413855642109.462, "dur": 603.325, + "args": { + "External id": 1445242,"Record function id": 0, "Ev Idx": 10617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413855642127.655, "dur": 572.674, + "args": { + "External id": 1445243,"Record function id": 0, "Ev Idx": 10618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855642197.884, "dur": 6.175, + "args": { + "External id": 1445244,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855642220.311, "dur": 29.743, + "args": { + "External id": 1445245,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642226.209, "dur": 2.016, + "args": { + "External id": 1445246,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642229.827, "dur": 0.560, + "args": { + "External id": 1445247,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642232.696, "dur": 0.455, + "args": { + "External id": 1445248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642234.730, "dur": 2.394, + "args": { + "External id": 1445249,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642238.011, "dur": 0.533, + "args": { + "External id": 1445250,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642240.002, "dur": 0.508, + "args": { + "External id": 1445251,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642241.981, "dur": 0.442, + "args": { + "External id": 1445252,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642243.575, "dur": 0.453, + "args": { + "External id": 1445253,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642245.689, "dur": 0.458, + "args": { + "External id": 1445254,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855642261.523, "dur": 42.373, + "args": { + "External id": 1445255,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855642335.751, "dur": 105.973, + "args": { + "External id": 1445256,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855642346.089, "dur": 3.023, + "args": { + "External id": 1445257,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855642354.206, "dur": 9.904, + "args": { + "External id": 1445258,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855642358.366, "dur": 5.250, + "args": { + "External id": 1445259,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642361.944, "dur": 0.531, + "args": { + "External id": 1445260,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855642370.902, "dur": 24.954, + "args": { + "External id": 1445261,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642372.867, "dur": 2.201, + "args": { + "External id": 1445262,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642376.217, "dur": 0.565, + "args": { + "External id": 1445263,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642378.470, "dur": 0.485, + "args": { + "External id": 1445264,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642380.574, "dur": 0.834, + "args": { + "External id": 1445265,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642382.548, "dur": 0.482, + "args": { + "External id": 1445266,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642384.855, "dur": 0.471, + "args": { + "External id": 1445267,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642386.816, "dur": 0.431, + "args": { + "External id": 1445268,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642388.533, "dur": 0.444, + "args": { + "External id": 1445269,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855642390.622, "dur": 2.768, + "args": { + "External id": 1445270,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855642404.956, "dur": 29.388, + "args": { + "External id": 1445271,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855642485.007, "dur": 143.431, + "args": { + "External id": 1445272,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855642535.989, "dur": 88.976, + "args": { + "External id": 1445273,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10648, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855642546.431, "dur": 74.065, + "args": { + "External id": 1445274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855642645.953, "dur": 2.162, + "args": { + "External id": 1445275,"Record function id": 0, "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": 10650, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855642727.184, "dur": 1873.995, + "args": { + "External id": 1445276,"Sequence number": 15348901, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10651 + } + }, + { + "ph": "f", "id": 434, "pid": 2338706, "tid": 2379422, "ts": 6413855642727.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855642839.448, "dur": 104.623, + "args": { + "External id": 1445277,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855643007.683, "dur": 82.038, + "args": { + "External id": 1445278,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643116.173, "dur": 61.704, + "args": { + "External id": 1445279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643189.162, "dur": 32.354, + "args": { + "External id": 1445280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643227.974, "dur": 33.374, + "args": { + "External id": 1445281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643268.298, "dur": 28.462, + "args": { + "External id": 1445282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643305.765, "dur": 32.831, + "args": { + "External id": 1445283,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855643368.119, "dur": 30.270, + "args": { + "External id": 1445284,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855643434.113, "dur": 33.629, + "args": { + "External id": 1445285,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855643491.454, "dur": 20.248, + "args": { + "External id": 1445286,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855643527.777, "dur": 16.191, + "args": { + "External id": 1445287,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643555.801, "dur": 39.532, + "args": { + "External id": 1445288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855643599.215, "dur": 35.299, + "args": { + "External id": 1445289,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855643664.522, "dur": 256.269, + "args": { + "External id": 1445290,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855643745.529, "dur": 6.884, + "args": { + "External id": 1445291,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855643755.177, "dur": 2.936, + "args": { + "External id": 1445292,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855643759.841, "dur": 2.161, + "args": { + "External id": 1445293,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855643763.204, "dur": 4.550, + "args": { + "External id": 1445294,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855643816.466, "dur": 4.718, + "args": { + "External id": 1445295,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855643818.187, "dur": 2.849, + "args": { + "External id": 1445296,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855643823.223, "dur": 32.663, + "args": { + "External id": 1445297,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855643828.259, "dur": 1.644, + "args": { + "External id": 1445298,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855643857.330, "dur": 2.057, + "args": { + "External id": 1445299,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855643858.545, "dur": 0.754, + "args": { + "External id": 1445300,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855643860.584, "dur": 16.073, + "args": { + "External id": 1445301,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855643862.520, "dur": 0.544, + "args": { + "External id": 1445302,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855643957.145, "dur": 49.781, + "args": { + "External id": 1445303,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855644027.098, "dur": 20.595, + "args": { + "External id": 1445304,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855644092.882, "dur": 52.429, + "args": { + "External id": 1445305,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855644153.442, "dur": 58.985, + "args": { + "External id": 1445306,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855644233.680, "dur": 24.938, + "args": { + "External id": 1445307,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855644265.954, "dur": 36.375, + "args": { + "External id": 1445308,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855644310.558, "dur": 27.941, + "args": { + "External id": 1445309,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855644345.925, "dur": 35.770, + "args": { + "External id": 1445310,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855644403.948, "dur": 27.882, + "args": { + "External id": 1445311,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855644449.876, "dur": 27.005, + "args": { + "External id": 1445312,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855644493.331, "dur": 17.432, + "args": { + "External id": 1445313,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855644524.149, "dur": 14.973, + "args": { + "External id": 1445314,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855644551.371, "dur": 16.937, + "args": { + "External id": 1445315,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644651.971, "dur": 16.370, + "args": { + "External id": 1445316,"Record function id": 0, "Ev Idx": 10691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644655.824, "dur": 11.620, + "args": { + "External id": 1445317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644660.248, "dur": 6.265, + "args": { + "External id": 1445318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644662.043, "dur": 4.360, + "args": { + "External id": 1445319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644672.383, "dur": 5.877, + "args": { + "External id": 1445320,"Record function id": 0, "Ev Idx": 10695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644673.944, "dur": 3.817, + "args": { + "External id": 1445321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644675.208, "dur": 2.023, + "args": { + "External id": 1445322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644675.970, "dur": 1.157, + "args": { + "External id": 1445323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644681.654, "dur": 5.590, + "args": { + "External id": 1445324,"Record function id": 0, "Ev Idx": 10699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644683.568, "dur": 3.198, + "args": { + "External id": 1445325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644684.155, "dur": 2.021, + "args": { + "External id": 1445326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644684.938, "dur": 1.161, + "args": { + "External id": 1445327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644690.565, "dur": 5.539, + "args": { + "External id": 1445328,"Record function id": 0, "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644692.040, "dur": 3.639, + "args": { + "External id": 1445329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644692.753, "dur": 2.273, + "args": { + "External id": 1445330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644693.719, "dur": 1.225, + "args": { + "External id": 1445331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644699.299, "dur": 5.617, + "args": { + "External id": 1445332,"Record function id": 0, "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644700.714, "dur": 3.780, + "args": { + "External id": 1445333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644701.145, "dur": 2.538, + "args": { + "External id": 1445334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644702.291, "dur": 1.310, + "args": { + "External id": 1445335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644708.005, "dur": 7.745, + "args": { + "External id": 1445336,"Record function id": 0, "Ev Idx": 10711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644709.659, "dur": 5.684, + "args": { + "External id": 1445337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644710.098, "dur": 4.630, + "args": { + "External id": 1445338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644710.984, "dur": 3.647, + "args": { + "External id": 1445339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644718.988, "dur": 5.603, + "args": { + "External id": 1445340,"Record function id": 0, "Ev Idx": 10715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644720.291, "dur": 3.894, + "args": { + "External id": 1445341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644720.712, "dur": 2.610, + "args": { + "External id": 1445342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644721.957, "dur": 1.283, + "args": { + "External id": 1445343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644728.247, "dur": 5.384, + "args": { + "External id": 1445344,"Record function id": 0, "Ev Idx": 10719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644729.797, "dur": 3.415, + "args": { + "External id": 1445345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644730.432, "dur": 2.338, + "args": { + "External id": 1445346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644731.376, "dur": 1.309, + "args": { + "External id": 1445347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644737.005, "dur": 5.556, + "args": { + "External id": 1445348,"Record function id": 0, "Ev Idx": 10723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855644738.503, "dur": 3.628, + "args": { + "External id": 1445349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644739.194, "dur": 2.271, + "args": { + "External id": 1445350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855644740.278, "dur": 1.101, + "args": { + "External id": 1445351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855644747.015, "dur": 62667.105, + "args": { + "External id": 1445352,"Record function id": 0, "Sequence number": 15348900, "Fwd thread id": 1, "Ev Idx": 10727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855644748.568, "dur": 62656.211, + "args": { + "External id": 1445353,"Sequence number": 15348900, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10728 + } + }, + { + "ph": "f", "id": 435, "pid": 2338706, "tid": 2379422, "ts": 6413855644748.568, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413855644778.533, "dur": 40.091, + "args": { + "External id": 1445354,"Record function id": 0, "Ev Idx": 10729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413855644826.750, "dur": 69.777, + "args": { + "External id": 1445355,"Record function id": 0, "Ev Idx": 10730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 2338706, "tid": 2379422, + "ts": 6413855644902.461, "dur": 62494.255, + "args": { + "External id": 1445356,"Record function id": 0, "Ev Idx": 10731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855645018.294, "dur": 7.579, + "args": { + "External id": 1445357,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855645036.492, "dur": 5.044, + "args": { + "External id": 1445358,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855645092.303, "dur": 61331.579, + "args": { + "External id": 1445359,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855645108.225, "dur": 61302.525, + "args": { + "External id": 1445360,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855645224.775, "dur": 19.697, + "args": { + "External id": 1445361,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855645264.372, "dur": 61102.074, + "args": { + "External id": 1445362,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855645269.759, "dur": 61095.694, + "args": { + "External id": 1445363,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855645274.198, "dur": 10.105, + "args": { + "External id": 1445364,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855645286.321, "dur": 61073.715, + "args": { + "External id": 1445365,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855706538.160, "dur": 12.530, + "args": { + "External id": 1445366,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855706541.715, "dur": 8.553, + "args": { + "External id": 1445367,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855706584.025, "dur": 306.597, + "args": { + "External id": 1445368,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855706618.389, "dur": 267.210, + "args": { + "External id": 1445369,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10744, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855706630.802, "dur": 249.585, + "args": { + "External id": 1445370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855706910.784, "dur": 2.271, + "args": { + "External id": 1445371,"Record function id": 0, "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": 10746, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855706971.708, "dur": 25.032, + "args": { + "External id": 1445372,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707011.659, "dur": 37.218, + "args": { + "External id": 1445373,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707097.185, "dur": 5.310, + "args": { + "External id": 1445374,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707109.851, "dur": 17.372, + "args": { + "External id": 1445375,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707133.488, "dur": 0.989, + "args": { + "External id": 1445376,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707182.666, "dur": 15.075, + "args": { + "External id": 1445377,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707206.831, "dur": 1.137, + "args": { + "External id": 1445378,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707213.122, "dur": 11.654, + "args": { + "External id": 1445379,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707229.304, "dur": 0.718, + "args": { + "External id": 1445380,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707233.734, "dur": 12.721, + "args": { + "External id": 1445381,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707250.528, "dur": 0.982, + "args": { + "External id": 1445382,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707255.924, "dur": 11.504, + "args": { + "External id": 1445383,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707271.620, "dur": 0.956, + "args": { + "External id": 1445384,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707276.839, "dur": 12.508, + "args": { + "External id": 1445385,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707295.484, "dur": 0.932, + "args": { + "External id": 1445386,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707300.648, "dur": 11.811, + "args": { + "External id": 1445387,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707316.548, "dur": 0.756, + "args": { + "External id": 1445388,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707321.265, "dur": 12.085, + "args": { + "External id": 1445389,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855707430.791, "dur": 3053.206, + "args": { + "External id": 1445390,"Record function id": 0, "Ev Idx": 10765 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413855707452.263, "dur": 1084.405, + "args": { + "External id": 1445391,"Record function id": 0, "Ev Idx": 10766 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413855707468.403, "dur": 327.520, + "args": { + "External id": 1445392,"Record function id": 0, "Ev Idx": 10767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707564.721, "dur": 7.008, + "args": { + "External id": 1445393,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707574.818, "dur": 0.985, + "args": { + "External id": 1445394,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707577.956, "dur": 1.117, + "args": { + "External id": 1445395,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707580.500, "dur": 0.843, + "args": { + "External id": 1445396,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707583.212, "dur": 0.803, + "args": { + "External id": 1445397,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707585.280, "dur": 0.647, + "args": { + "External id": 1445398,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707589.627, "dur": 0.718, + "args": { + "External id": 1445399,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707591.783, "dur": 1.863, + "args": { + "External id": 1445400,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707594.983, "dur": 2.670, + "args": { + "External id": 1445401,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855707598.852, "dur": 0.659, + "args": { + "External id": 1445402,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855707620.292, "dur": 145.901, + "args": { + "External id": 1445403,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855707638.223, "dur": 123.621, + "args": { + "External id": 1445404,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855707654.062, "dur": 15.461, + "args": { + "External id": 1445405,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855707673.181, "dur": 61.985, + "args": { + "External id": 1445406,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855707678.352, "dur": 56.447, + "args": { + "External id": 1445407,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855707682.280, "dur": 5.540, + "args": { + "External id": 1445408,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855707689.549, "dur": 44.769, + "args": { + "External id": 1445409,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 2338706, "tid": 2379422, + "ts": 6413855707886.868, "dur": 642.062, + "args": { + "External id": 1445410,"Record function id": 0, "Ev Idx": 10785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413855707907.370, "dur": 608.408, + "args": { + "External id": 1445411,"Record function id": 0, "Ev Idx": 10786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855707970.814, "dur": 5.901, + "args": { + "External id": 1445412,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855708010.421, "dur": 30.561, + "args": { + "External id": 1445413,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708016.121, "dur": 2.013, + "args": { + "External id": 1445414,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708020.802, "dur": 0.639, + "args": { + "External id": 1445415,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708022.595, "dur": 0.491, + "args": { + "External id": 1445416,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708024.797, "dur": 2.751, + "args": { + "External id": 1445417,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708029.342, "dur": 0.402, + "args": { + "External id": 1445418,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708030.939, "dur": 0.400, + "args": { + "External id": 1445419,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708033.429, "dur": 0.563, + "args": { + "External id": 1445420,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708035.362, "dur": 0.347, + "args": { + "External id": 1445421,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708036.992, "dur": 0.355, + "args": { + "External id": 1445422,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855708052.466, "dur": 77.811, + "args": { + "External id": 1445423,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855708165.549, "dur": 114.361, + "args": { + "External id": 1445424,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855708177.180, "dur": 4.702, + "args": { + "External id": 1445425,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855708187.343, "dur": 11.045, + "args": { + "External id": 1445426,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855708191.732, "dur": 6.144, + "args": { + "External id": 1445427,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708195.423, "dur": 1.030, + "args": { + "External id": 1445428,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855708205.028, "dur": 26.436, + "args": { + "External id": 1445429,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708207.130, "dur": 2.522, + "args": { + "External id": 1445430,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708211.569, "dur": 0.773, + "args": { + "External id": 1445431,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708214.319, "dur": 0.423, + "args": { + "External id": 1445432,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708216.339, "dur": 0.398, + "args": { + "External id": 1445433,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708218.043, "dur": 0.560, + "args": { + "External id": 1445434,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708220.475, "dur": 0.362, + "args": { + "External id": 1445435,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708222.168, "dur": 0.329, + "args": { + "External id": 1445436,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708223.563, "dur": 0.378, + "args": { + "External id": 1445437,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855708226.041, "dur": 2.835, + "args": { + "External id": 1445438,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855708242.110, "dur": 30.099, + "args": { + "External id": 1445439,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855708328.524, "dur": 120.104, + "args": { + "External id": 1445440,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855708354.777, "dur": 90.337, + "args": { + "External id": 1445441,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10816, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855708364.651, "dur": 75.981, + "args": { + "External id": 1445442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855708463.705, "dur": 1.746, + "args": { + "External id": 1445443,"Record function id": 0, "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": 10818, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855708544.521, "dur": 1915.677, + "args": { + "External id": 1445444,"Sequence number": 15348899, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10819 + } + }, + { + "ph": "f", "id": 436, "pid": 2338706, "tid": 2379422, "ts": 6413855708544.521, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855708655.846, "dur": 102.627, + "args": { + "External id": 1445445,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855708802.948, "dur": 40.984, + "args": { + "External id": 1445446,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855708863.274, "dur": 47.988, + "args": { + "External id": 1445447,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855708920.987, "dur": 30.932, + "args": { + "External id": 1445448,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855708958.100, "dur": 51.090, + "args": { + "External id": 1445449,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709019.462, "dur": 30.979, + "args": { + "External id": 1445450,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709115.355, "dur": 37.228, + "args": { + "External id": 1445451,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855709188.739, "dur": 27.772, + "args": { + "External id": 1445452,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855709236.977, "dur": 31.034, + "args": { + "External id": 1445453,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855709291.240, "dur": 20.070, + "args": { + "External id": 1445454,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855709325.506, "dur": 15.341, + "args": { + "External id": 1445455,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709352.366, "dur": 38.398, + "args": { + "External id": 1445456,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709394.362, "dur": 34.574, + "args": { + "External id": 1445457,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855709463.931, "dur": 258.899, + "args": { + "External id": 1445458,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 10833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855709546.952, "dur": 9.783, + "args": { + "External id": 1445459,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855709558.947, "dur": 3.510, + "args": { + "External id": 1445460,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855709563.847, "dur": 3.030, + "args": { + "External id": 1445461,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855709568.036, "dur": 4.482, + "args": { + "External id": 1445462,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855709617.946, "dur": 4.887, + "args": { + "External id": 1445463,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855709619.917, "dur": 2.758, + "args": { + "External id": 1445464,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855709624.622, "dur": 33.368, + "args": { + "External id": 1445465,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855709630.499, "dur": 1.767, + "args": { + "External id": 1445466,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855709659.414, "dur": 2.046, + "args": { + "External id": 1445467,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855709660.629, "dur": 0.740, + "args": { + "External id": 1445468,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 10843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855709662.651, "dur": 16.465, + "args": { + "External id": 1445469,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 10844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855709664.396, "dur": 0.663, + "args": { + "External id": 1445470,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 10845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855709758.616, "dur": 27.731, + "args": { + "External id": 1445471,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855709842.738, "dur": 21.093, + "args": { + "External id": 1445472,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709872.798, "dur": 42.108, + "args": { + "External id": 1445473,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709922.202, "dur": 39.835, + "args": { + "External id": 1445474,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855709973.725, "dur": 44.554, + "args": { + "External id": 1445475,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 10850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855710047.176, "dur": 100.638, + "args": { + "External id": 1445476,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 10851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855710163.306, "dur": 33.408, + "args": { + "External id": 1445477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855710204.749, "dur": 33.272, + "args": { + "External id": 1445478,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 10853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855710261.663, "dur": 27.919, + "args": { + "External id": 1445479,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 10854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855710306.615, "dur": 26.201, + "args": { + "External id": 1445480,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855710347.766, "dur": 17.213, + "args": { + "External id": 1445481,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855710380.133, "dur": 14.456, + "args": { + "External id": 1445482,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855710407.848, "dur": 16.584, + "args": { + "External id": 1445483,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 10858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710508.963, "dur": 17.261, + "args": { + "External id": 1445484,"Record function id": 0, "Ev Idx": 10859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710512.817, "dur": 12.371, + "args": { + "External id": 1445485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710517.566, "dur": 6.604, + "args": { + "External id": 1445486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710519.711, "dur": 4.337, + "args": { + "External id": 1445487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710530.175, "dur": 6.234, + "args": { + "External id": 1445488,"Record function id": 0, "Ev Idx": 10863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710532.131, "dur": 3.799, + "args": { + "External id": 1445489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710532.831, "dur": 2.444, + "args": { + "External id": 1445490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710533.845, "dur": 1.279, + "args": { + "External id": 1445491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710539.714, "dur": 5.664, + "args": { + "External id": 1445492,"Record function id": 0, "Ev Idx": 10867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710541.527, "dur": 3.427, + "args": { + "External id": 1445493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710542.200, "dur": 2.258, + "args": { + "External id": 1445494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710543.145, "dur": 1.235, + "args": { + "External id": 1445495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 10870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710548.604, "dur": 4.918, + "args": { + "External id": 1445496,"Record function id": 0, "Ev Idx": 10871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710550.126, "dur": 2.973, + "args": { + "External id": 1445497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710550.619, "dur": 2.056, + "args": { + "External id": 1445498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710551.478, "dur": 1.113, + "args": { + "External id": 1445499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 10874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710556.643, "dur": 7.388, + "args": { + "External id": 1445500,"Record function id": 0, "Ev Idx": 10875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710558.173, "dur": 5.413, + "args": { + "External id": 1445501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710558.642, "dur": 4.274, + "args": { + "External id": 1445502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710559.317, "dur": 3.514, + "args": { + "External id": 1445503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710567.126, "dur": 4.210, + "args": { + "External id": 1445504,"Record function id": 0, "Ev Idx": 10879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710568.109, "dur": 2.803, + "args": { + "External id": 1445505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710568.641, "dur": 1.812, + "args": { + "External id": 1445506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710569.419, "dur": 0.941, + "args": { + "External id": 1445507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 10882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710574.758, "dur": 4.741, + "args": { + "External id": 1445508,"Record function id": 0, "Ev Idx": 10883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710576.281, "dur": 2.780, + "args": { + "External id": 1445509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710576.749, "dur": 1.728, + "args": { + "External id": 1445510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710577.541, "dur": 0.856, + "args": { + "External id": 1445511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710583.615, "dur": 3.840, + "args": { + "External id": 1445512,"Record function id": 0, "Ev Idx": 10887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710584.860, "dur": 2.195, + "args": { + "External id": 1445513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710585.490, "dur": 1.109, + "args": { + "External id": 1445514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710585.851, "dur": 0.685, + "args": { + "External id": 1445515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 10890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710591.241, "dur": 3.665, + "args": { + "External id": 1445516,"Record function id": 0, "Ev Idx": 10891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855710592.579, "dur": 1.920, + "args": { + "External id": 1445517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710593.081, "dur": 0.965, + "args": { + "External id": 1445518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855710593.366, "dur": 0.616, + "args": { + "External id": 1445519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 10894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855710599.179, "dur": 61124.116, + "args": { + "External id": 1445520,"Record function id": 0, "Sequence number": 15348898, "Fwd thread id": 1, "Ev Idx": 10895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855710600.344, "dur": 61113.698, + "args": { + "External id": 1445521,"Sequence number": 15348898, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10896 + } + }, + { + "ph": "f", "id": 437, "pid": 2338706, "tid": 2379422, "ts": 6413855710600.344, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413855710631.632, "dur": 40.200, + "args": { + "External id": 1445522,"Record function id": 0, "Ev Idx": 10897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413855710680.592, "dur": 72.494, + "args": { + "External id": 1445523,"Record function id": 0, "Ev Idx": 10898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 2338706, "tid": 2379422, + "ts": 6413855710758.985, "dur": 60947.259, + "args": { + "External id": 1445524,"Record function id": 0, "Ev Idx": 10899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855710854.253, "dur": 7.150, + "args": { + "External id": 1445525,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855710870.944, "dur": 4.791, + "args": { + "External id": 1445526,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855710893.454, "dur": 59815.390, + "args": { + "External id": 1445527,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855710907.628, "dur": 59787.892, + "args": { + "External id": 1445528,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 10903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855711131.084, "dur": 21.751, + "args": { + "External id": 1445529,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855711173.784, "dur": 59477.778, + "args": { + "External id": 1445530,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 10905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855711176.609, "dur": 59473.977, + "args": { + "External id": 1445531,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 10906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855711181.716, "dur": 12.367, + "args": { + "External id": 1445532,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855711196.284, "dur": 59449.679, + "args": { + "External id": 1445533,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 10908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855770822.773, "dur": 12.383, + "args": { + "External id": 1445534,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 10909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855770826.377, "dur": 8.378, + "args": { + "External id": 1445535,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855770868.805, "dur": 438.243, + "args": { + "External id": 1445536,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 10911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855770902.262, "dur": 398.528, + "args": { + "External id": 1445537,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10912, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855770913.743, "dur": 380.849, + "args": { + "External id": 1445538,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 10913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855771333.703, "dur": 2.236, + "args": { + "External id": 1445539,"Record function id": 0, "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": 10914, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771400.973, "dur": 8.829, + "args": { + "External id": 1445540,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771422.597, "dur": 36.427, + "args": { + "External id": 1445541,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771469.400, "dur": 1.407, + "args": { + "External id": 1445542,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771476.787, "dur": 12.753, + "args": { + "External id": 1445543,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771495.536, "dur": 0.891, + "args": { + "External id": 1445544,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771501.247, "dur": 12.727, + "args": { + "External id": 1445545,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771518.810, "dur": 0.871, + "args": { + "External id": 1445546,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771523.914, "dur": 11.489, + "args": { + "External id": 1445547,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 10922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771539.497, "dur": 1.033, + "args": { + "External id": 1445548,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771544.508, "dur": 11.772, + "args": { + "External id": 1445549,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 10924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771560.566, "dur": 1.127, + "args": { + "External id": 1445550,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771566.378, "dur": 11.347, + "args": { + "External id": 1445551,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 10926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771582.349, "dur": 0.937, + "args": { + "External id": 1445552,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771589.760, "dur": 12.897, + "args": { + "External id": 1445553,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771606.806, "dur": 0.706, + "args": { + "External id": 1445554,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771611.938, "dur": 11.321, + "args": { + "External id": 1445555,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 10930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771627.451, "dur": 3.228, + "args": { + "External id": 1445556,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855771634.219, "dur": 11.991, + "args": { + "External id": 1445557,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 10932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855771738.329, "dur": 2969.192, + "args": { + "External id": 1445558,"Record function id": 0, "Ev Idx": 10933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413855771759.268, "dur": 1088.244, + "args": { + "External id": 1445559,"Record function id": 0, "Ev Idx": 10934 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413855771774.768, "dur": 388.223, + "args": { + "External id": 1445560,"Record function id": 0, "Ev Idx": 10935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771863.603, "dur": 4.134, + "args": { + "External id": 1445561,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 10936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771870.831, "dur": 0.949, + "args": { + "External id": 1445562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771873.627, "dur": 0.972, + "args": { + "External id": 1445563,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771878.365, "dur": 0.810, + "args": { + "External id": 1445564,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771880.755, "dur": 0.767, + "args": { + "External id": 1445565,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 10940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771883.117, "dur": 0.909, + "args": { + "External id": 1445566,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 10941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771885.614, "dur": 0.876, + "args": { + "External id": 1445567,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 10942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771889.690, "dur": 4.307, + "args": { + "External id": 1445568,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771895.464, "dur": 0.861, + "args": { + "External id": 1445569,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855771898.322, "dur": 1.098, + "args": { + "External id": 1445570,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 10945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855771916.922, "dur": 208.041, + "args": { + "External id": 1445571,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855771934.326, "dur": 184.805, + "args": { + "External id": 1445572,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 10947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855771949.697, "dur": 15.640, + "args": { + "External id": 1445573,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855771969.192, "dur": 119.147, + "args": { + "External id": 1445574,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 10949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855771972.202, "dur": 115.762, + "args": { + "External id": 1445575,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 10950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855771976.328, "dur": 24.490, + "args": { + "External id": 1445576,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855772003.505, "dur": 83.381, + "args": { + "External id": 1445577,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 10952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 2338706, "tid": 2379422, + "ts": 6413855772264.704, "dur": 574.455, + "args": { + "External id": 1445578,"Record function id": 0, "Ev Idx": 10953 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413855772284.567, "dur": 541.945, + "args": { + "External id": 1445579,"Record function id": 0, "Ev Idx": 10954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855772351.540, "dur": 6.055, + "args": { + "External id": 1445580,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855772372.508, "dur": 30.850, + "args": { + "External id": 1445581,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772378.135, "dur": 1.956, + "args": { + "External id": 1445582,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772382.660, "dur": 0.675, + "args": { + "External id": 1445583,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772385.268, "dur": 2.113, + "args": { + "External id": 1445584,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772388.369, "dur": 0.774, + "args": { + "External id": 1445585,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772390.932, "dur": 0.425, + "args": { + "External id": 1445586,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772393.118, "dur": 0.415, + "args": { + "External id": 1445587,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772394.675, "dur": 0.399, + "args": { + "External id": 1445588,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772397.043, "dur": 0.414, + "args": { + "External id": 1445589,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772399.013, "dur": 0.834, + "args": { + "External id": 1445590,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855772415.252, "dur": 40.630, + "args": { + "External id": 1445591,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855772485.831, "dur": 110.620, + "args": { + "External id": 1445592,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 10967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855772496.063, "dur": 3.269, + "args": { + "External id": 1445593,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855772504.741, "dur": 12.648, + "args": { + "External id": 1445594,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855772509.189, "dur": 7.767, + "args": { + "External id": 1445595,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 10970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772512.808, "dur": 2.954, + "args": { + "External id": 1445596,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 10971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855772523.674, "dur": 27.273, + "args": { + "External id": 1445597,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 10972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772525.886, "dur": 0.657, + "args": { + "External id": 1445598,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772528.153, "dur": 0.501, + "args": { + "External id": 1445599,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772530.185, "dur": 0.438, + "args": { + "External id": 1445600,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772532.344, "dur": 0.474, + "args": { + "External id": 1445601,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772534.047, "dur": 0.416, + "args": { + "External id": 1445602,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772536.316, "dur": 0.611, + "args": { + "External id": 1445603,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772541.586, "dur": 0.400, + "args": { + "External id": 1445604,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772543.503, "dur": 2.620, + "args": { + "External id": 1445605,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855772547.799, "dur": 0.700, + "args": { + "External id": 1445606,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 10981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855772560.482, "dur": 28.776, + "args": { + "External id": 1445607,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 10982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855772641.160, "dur": 117.478, + "args": { + "External id": 1445608,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 10983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855772669.000, "dur": 86.416, + "args": { + "External id": 1445609,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 10984, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855772678.561, "dur": 72.481, + "args": { + "External id": 1445610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 10985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855772776.165, "dur": 1.905, + "args": { + "External id": 1445611,"Record function id": 0, "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": 10986, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855772854.801, "dur": 1828.347, + "args": { + "External id": 1445612,"Sequence number": 15348897, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 10987 + } + }, + { + "ph": "f", "id": 438, "pid": 2338706, "tid": 2379422, "ts": 6413855772854.801, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855772966.570, "dur": 161.131, + "args": { + "External id": 1445613,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 10988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855773177.637, "dur": 43.235, + "args": { + "External id": 1445614,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 10989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773242.294, "dur": 55.025, + "args": { + "External id": 1445615,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 10990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773326.346, "dur": 35.737, + "args": { + "External id": 1445616,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773369.347, "dur": 32.055, + "args": { + "External id": 1445617,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773408.126, "dur": 27.293, + "args": { + "External id": 1445618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 10993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773444.439, "dur": 28.665, + "args": { + "External id": 1445619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 10994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855773502.934, "dur": 25.652, + "args": { + "External id": 1445620,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 10995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855773548.964, "dur": 28.746, + "args": { + "External id": 1445621,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 10996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855773602.152, "dur": 19.878, + "args": { + "External id": 1445622,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 10997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855773637.428, "dur": 15.353, + "args": { + "External id": 1445623,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 10998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773663.668, "dur": 35.978, + "args": { + "External id": 1445624,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 10999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855773703.660, "dur": 33.229, + "args": { + "External id": 1445625,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855773766.421, "dur": 274.419, + "args": { + "External id": 1445626,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855773849.868, "dur": 7.029, + "args": { + "External id": 1445627,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855773858.880, "dur": 2.901, + "args": { + "External id": 1445628,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855773863.034, "dur": 2.103, + "args": { + "External id": 1445629,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855773866.448, "dur": 4.526, + "args": { + "External id": 1445630,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855773915.815, "dur": 4.782, + "args": { + "External id": 1445631,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855773917.844, "dur": 2.546, + "args": { + "External id": 1445632,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855773922.626, "dur": 32.427, + "args": { + "External id": 1445633,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855773928.217, "dur": 1.989, + "args": { + "External id": 1445634,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855773956.533, "dur": 2.122, + "args": { + "External id": 1445635,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855773957.769, "dur": 0.784, + "args": { + "External id": 1445636,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855773959.758, "dur": 14.494, + "args": { + "External id": 1445637,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855773961.790, "dur": 0.672, + "args": { + "External id": 1445638,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855774120.680, "dur": 31.055, + "args": { + "External id": 1445639,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855774170.066, "dur": 16.474, + "args": { + "External id": 1445640,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855774195.211, "dur": 47.252, + "args": { + "External id": 1445641,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855774250.035, "dur": 39.497, + "args": { + "External id": 1445642,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855774299.812, "dur": 32.406, + "args": { + "External id": 1445643,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855774345.802, "dur": 41.445, + "args": { + "External id": 1445644,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855774396.090, "dur": 31.972, + "args": { + "External id": 1445645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855774435.692, "dur": 33.907, + "args": { + "External id": 1445646,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855774489.454, "dur": 29.131, + "args": { + "External id": 1445647,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855774535.479, "dur": 25.644, + "args": { + "External id": 1445648,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855774576.382, "dur": 18.638, + "args": { + "External id": 1445649,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855774608.233, "dur": 14.428, + "args": { + "External id": 1445650,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855774634.869, "dur": 15.998, + "args": { + "External id": 1445651,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774731.178, "dur": 16.163, + "args": { + "External id": 1445652,"Record function id": 0, "Ev Idx": 11027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774734.909, "dur": 11.374, + "args": { + "External id": 1445653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774739.389, "dur": 5.859, + "args": { + "External id": 1445654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774741.036, "dur": 4.052, + "args": { + "External id": 1445655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774751.362, "dur": 6.543, + "args": { + "External id": 1445656,"Record function id": 0, "Ev Idx": 11031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774753.222, "dur": 4.190, + "args": { + "External id": 1445657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774754.241, "dur": 2.608, + "args": { + "External id": 1445658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774755.382, "dur": 1.368, + "args": { + "External id": 1445659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774761.236, "dur": 5.152, + "args": { + "External id": 1445660,"Record function id": 0, "Ev Idx": 11035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774762.756, "dur": 3.230, + "args": { + "External id": 1445661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774763.261, "dur": 2.116, + "args": { + "External id": 1445662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774764.272, "dur": 1.011, + "args": { + "External id": 1445663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774769.536, "dur": 4.994, + "args": { + "External id": 1445664,"Record function id": 0, "Ev Idx": 11039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774770.476, "dur": 3.619, + "args": { + "External id": 1445665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774771.176, "dur": 2.267, + "args": { + "External id": 1445666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774772.099, "dur": 1.266, + "args": { + "External id": 1445667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774777.596, "dur": 4.611, + "args": { + "External id": 1445668,"Record function id": 0, "Ev Idx": 11043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774778.973, "dur": 2.830, + "args": { + "External id": 1445669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774779.574, "dur": 1.649, + "args": { + "External id": 1445670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774780.476, "dur": 0.681, + "args": { + "External id": 1445671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774785.231, "dur": 6.081, + "args": { + "External id": 1445672,"Record function id": 0, "Ev Idx": 11047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774786.516, "dur": 4.357, + "args": { + "External id": 1445673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774787.083, "dur": 3.205, + "args": { + "External id": 1445674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774787.533, "dur": 2.684, + "args": { + "External id": 1445675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774794.616, "dur": 4.165, + "args": { + "External id": 1445676,"Record function id": 0, "Ev Idx": 11051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774796.185, "dur": 2.206, + "args": { + "External id": 1445677,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774796.804, "dur": 1.039, + "args": { + "External id": 1445678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774797.095, "dur": 0.681, + "args": { + "External id": 1445679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774802.058, "dur": 3.864, + "args": { + "External id": 1445680,"Record function id": 0, "Ev Idx": 11055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774803.325, "dur": 2.198, + "args": { + "External id": 1445681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774803.766, "dur": 1.257, + "args": { + "External id": 1445682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774804.198, "dur": 0.756, + "args": { + "External id": 1445683,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774809.050, "dur": 4.156, + "args": { + "External id": 1445684,"Record function id": 0, "Ev Idx": 11059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855774810.436, "dur": 2.375, + "args": { + "External id": 1445685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774810.878, "dur": 1.524, + "args": { + "External id": 1445686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855774811.678, "dur": 0.610, + "args": { + "External id": 1445687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855774817.144, "dur": 61106.844, + "args": { + "External id": 1445688,"Record function id": 0, "Sequence number": 15348896, "Fwd thread id": 1, "Ev Idx": 11063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855774818.495, "dur": 61095.839, + "args": { + "External id": 1445689,"Sequence number": 15348896, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11064 + } + }, + { + "ph": "f", "id": 439, "pid": 2338706, "tid": 2379422, "ts": 6413855774818.495, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413855774846.903, "dur": 41.187, + "args": { + "External id": 1445690,"Record function id": 0, "Ev Idx": 11065 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413855774895.867, "dur": 68.891, + "args": { + "External id": 1445691,"Record function id": 0, "Ev Idx": 11066 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 2338706, "tid": 2379422, + "ts": 6413855774970.465, "dur": 60935.549, + "args": { + "External id": 1445692,"Record function id": 0, "Ev Idx": 11067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855775122.216, "dur": 8.990, + "args": { + "External id": 1445693,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855775143.524, "dur": 5.188, + "args": { + "External id": 1445694,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855775164.702, "dur": 59714.246, + "args": { + "External id": 1445695,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855775179.290, "dur": 59686.115, + "args": { + "External id": 1445696,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855775294.922, "dur": 16.839, + "args": { + "External id": 1445697,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855775331.392, "dur": 59488.811, + "args": { + "External id": 1445698,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855775334.232, "dur": 59485.006, + "args": { + "External id": 1445699,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855775339.094, "dur": 9.543, + "args": { + "External id": 1445700,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855775351.139, "dur": 59462.867, + "args": { + "External id": 1445701,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855835007.792, "dur": 13.362, + "args": { + "External id": 1445702,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855835011.394, "dur": 9.147, + "args": { + "External id": 1445703,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835083.495, "dur": 425.478, + "args": { + "External id": 1445704,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855835115.320, "dur": 388.348, + "args": { + "External id": 1445705,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11080, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855835129.782, "dur": 367.461, + "args": { + "External id": 1445706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855835531.044, "dur": 2.373, + "args": { + "External id": 1445707,"Record function id": 0, "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": 11082, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835597.746, "dur": 7.269, + "args": { + "External id": 1445708,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835618.438, "dur": 36.592, + "args": { + "External id": 1445709,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835665.212, "dur": 3.933, + "args": { + "External id": 1445710,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835675.362, "dur": 12.814, + "args": { + "External id": 1445711,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835693.965, "dur": 0.880, + "args": { + "External id": 1445712,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835699.056, "dur": 13.391, + "args": { + "External id": 1445713,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835718.031, "dur": 1.030, + "args": { + "External id": 1445714,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835723.279, "dur": 11.506, + "args": { + "External id": 1445715,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835739.359, "dur": 0.728, + "args": { + "External id": 1445716,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835744.462, "dur": 12.383, + "args": { + "External id": 1445717,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835760.852, "dur": 1.376, + "args": { + "External id": 1445718,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835767.107, "dur": 11.664, + "args": { + "External id": 1445719,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835782.702, "dur": 1.023, + "args": { + "External id": 1445720,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835790.158, "dur": 12.627, + "args": { + "External id": 1445721,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835807.112, "dur": 0.904, + "args": { + "External id": 1445722,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835812.364, "dur": 12.101, + "args": { + "External id": 1445723,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855835828.374, "dur": 0.875, + "args": { + "External id": 1445724,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855835833.072, "dur": 12.413, + "args": { + "External id": 1445725,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855835939.741, "dur": 2940.246, + "args": { + "External id": 1445726,"Record function id": 0, "Ev Idx": 11101 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413855835959.961, "dur": 1133.455, + "args": { + "External id": 1445727,"Record function id": 0, "Ev Idx": 11102 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413855835976.458, "dur": 395.606, + "args": { + "External id": 1445728,"Record function id": 0, "Ev Idx": 11103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836125.417, "dur": 7.605, + "args": { + "External id": 1445729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836136.792, "dur": 1.146, + "args": { + "External id": 1445730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836139.877, "dur": 0.882, + "args": { + "External id": 1445731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836144.706, "dur": 0.722, + "args": { + "External id": 1445732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836146.792, "dur": 1.002, + "args": { + "External id": 1445733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836149.225, "dur": 0.962, + "args": { + "External id": 1445734,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836152.656, "dur": 0.864, + "args": { + "External id": 1445735,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836156.799, "dur": 2.304, + "args": { + "External id": 1445736,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836160.398, "dur": 2.814, + "args": { + "External id": 1445737,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855836164.829, "dur": 0.767, + "args": { + "External id": 1445738,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855836184.477, "dur": 153.173, + "args": { + "External id": 1445739,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855836202.287, "dur": 130.549, + "args": { + "External id": 1445740,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855836219.525, "dur": 15.165, + "args": { + "External id": 1445741,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855836238.650, "dur": 67.261, + "args": { + "External id": 1445742,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855836241.335, "dur": 64.240, + "args": { + "External id": 1445743,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836245.526, "dur": 6.199, + "args": { + "External id": 1445744,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855836253.851, "dur": 50.987, + "args": { + "External id": 1445745,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11120 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 2338706, "tid": 2379422, + "ts": 6413855836466.543, "dur": 582.356, + "args": { + "External id": 1445746,"Record function id": 0, "Ev Idx": 11121 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413855836484.130, "dur": 551.515, + "args": { + "External id": 1445747,"Record function id": 0, "Ev Idx": 11122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855836551.289, "dur": 5.293, + "args": { + "External id": 1445748,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855836571.701, "dur": 28.442, + "args": { + "External id": 1445749,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836577.059, "dur": 1.662, + "args": { + "External id": 1445750,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836581.229, "dur": 0.683, + "args": { + "External id": 1445751,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836583.287, "dur": 0.450, + "args": { + "External id": 1445752,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836585.541, "dur": 1.905, + "args": { + "External id": 1445753,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836589.045, "dur": 0.396, + "args": { + "External id": 1445754,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836590.393, "dur": 0.628, + "args": { + "External id": 1445755,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836592.680, "dur": 0.407, + "args": { + "External id": 1445756,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836594.746, "dur": 0.512, + "args": { + "External id": 1445757,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836596.153, "dur": 0.404, + "args": { + "External id": 1445758,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855836610.479, "dur": 39.594, + "args": { + "External id": 1445759,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855836679.869, "dur": 103.512, + "args": { + "External id": 1445760,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 11135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855836689.674, "dur": 3.355, + "args": { + "External id": 1445761,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855836698.284, "dur": 10.366, + "args": { + "External id": 1445762,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855836702.754, "dur": 5.468, + "args": { + "External id": 1445763,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 11138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836706.631, "dur": 0.528, + "args": { + "External id": 1445764,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855836714.836, "dur": 23.845, + "args": { + "External id": 1445765,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836716.326, "dur": 2.548, + "args": { + "External id": 1445766,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836720.477, "dur": 0.450, + "args": { + "External id": 1445767,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836722.278, "dur": 0.387, + "args": { + "External id": 1445768,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836724.514, "dur": 0.380, + "args": { + "External id": 1445769,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836726.684, "dur": 0.516, + "args": { + "External id": 1445770,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836728.070, "dur": 0.384, + "args": { + "External id": 1445771,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836730.178, "dur": 0.381, + "args": { + "External id": 1445772,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836732.046, "dur": 0.334, + "args": { + "External id": 1445773,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855836733.494, "dur": 2.442, + "args": { + "External id": 1445774,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855836748.426, "dur": 27.880, + "args": { + "External id": 1445775,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855836826.693, "dur": 115.582, + "args": { + "External id": 1445776,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 11151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855836851.629, "dur": 87.199, + "args": { + "External id": 1445777,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11152, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855836861.251, "dur": 73.339, + "args": { + "External id": 1445778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 11153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855836959.949, "dur": 1.927, + "args": { + "External id": 1445779,"Record function id": 0, "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": 11154, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855837103.837, "dur": 1752.991, + "args": { + "External id": 1445780,"Sequence number": 15348895, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11155 + } + }, + { + "ph": "f", "id": 440, "pid": 2338706, "tid": 2379422, "ts": 6413855837103.837, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837220.167, "dur": 107.413, + "args": { + "External id": 1445781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855837390.235, "dur": 41.714, + "args": { + "External id": 1445782,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837452.814, "dur": 49.951, + "args": { + "External id": 1445783,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837512.503, "dur": 31.347, + "args": { + "External id": 1445784,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837550.179, "dur": 32.505, + "args": { + "External id": 1445785,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837588.918, "dur": 27.579, + "args": { + "External id": 1445786,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837626.414, "dur": 28.802, + "args": { + "External id": 1445787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855837683.153, "dur": 26.086, + "args": { + "External id": 1445788,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855837728.136, "dur": 29.701, + "args": { + "External id": 1445789,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855837778.606, "dur": 20.378, + "args": { + "External id": 1445790,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855837812.224, "dur": 17.648, + "args": { + "External id": 1445791,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837840.251, "dur": 36.825, + "args": { + "External id": 1445792,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855837880.896, "dur": 33.651, + "args": { + "External id": 1445793,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855837943.326, "dur": 326.095, + "args": { + "External id": 1445794,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855838046.206, "dur": 40.146, + "args": { + "External id": 1445795,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855838093.876, "dur": 3.297, + "args": { + "External id": 1445796,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855838098.309, "dur": 2.758, + "args": { + "External id": 1445797,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855838102.335, "dur": 4.804, + "args": { + "External id": 1445798,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855838158.117, "dur": 5.297, + "args": { + "External id": 1445799,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855838160.468, "dur": 2.764, + "args": { + "External id": 1445800,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855838165.169, "dur": 33.694, + "args": { + "External id": 1445801,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855838171.149, "dur": 1.711, + "args": { + "External id": 1445802,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855838200.774, "dur": 1.962, + "args": { + "External id": 1445803,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855838202.083, "dur": 0.569, + "args": { + "External id": 1445804,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855838204.221, "dur": 17.328, + "args": { + "External id": 1445805,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855838206.847, "dur": 0.805, + "args": { + "External id": 1445806,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855838307.379, "dur": 28.653, + "args": { + "External id": 1445807,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855838352.418, "dur": 17.843, + "args": { + "External id": 1445808,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855838378.739, "dur": 48.142, + "args": { + "External id": 1445809,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855838433.598, "dur": 53.467, + "args": { + "External id": 1445810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855838503.723, "dur": 27.756, + "args": { + "External id": 1445811,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855838539.912, "dur": 38.123, + "args": { + "External id": 1445812,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855838584.884, "dur": 29.123, + "args": { + "External id": 1445813,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855838620.862, "dur": 30.333, + "args": { + "External id": 1445814,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855838673.792, "dur": 26.254, + "args": { + "External id": 1445815,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855838715.502, "dur": 24.495, + "args": { + "External id": 1445816,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855838753.024, "dur": 17.517, + "args": { + "External id": 1445817,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855838783.219, "dur": 13.754, + "args": { + "External id": 1445818,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855838809.814, "dur": 15.745, + "args": { + "External id": 1445819,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838903.807, "dur": 15.782, + "args": { + "External id": 1445820,"Record function id": 0, "Ev Idx": 11195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838907.512, "dur": 11.048, + "args": { + "External id": 1445821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838911.843, "dur": 5.769, + "args": { + "External id": 1445822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838913.540, "dur": 3.854, + "args": { + "External id": 1445823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838923.420, "dur": 5.284, + "args": { + "External id": 1445824,"Record function id": 0, "Ev Idx": 11199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838924.847, "dur": 3.305, + "args": { + "External id": 1445825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838925.493, "dur": 2.028, + "args": { + "External id": 1445826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838926.195, "dur": 1.228, + "args": { + "External id": 1445827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838931.964, "dur": 4.853, + "args": { + "External id": 1445828,"Record function id": 0, "Ev Idx": 11203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838933.219, "dur": 3.173, + "args": { + "External id": 1445829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838933.721, "dur": 2.040, + "args": { + "External id": 1445830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838934.390, "dur": 1.269, + "args": { + "External id": 1445831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838940.120, "dur": 3.944, + "args": { + "External id": 1445832,"Record function id": 0, "Ev Idx": 11207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838941.221, "dur": 2.399, + "args": { + "External id": 1445833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838941.708, "dur": 1.272, + "args": { + "External id": 1445834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838942.125, "dur": 0.753, + "args": { + "External id": 1445835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838947.284, "dur": 4.346, + "args": { + "External id": 1445836,"Record function id": 0, "Ev Idx": 11211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838948.510, "dur": 2.694, + "args": { + "External id": 1445837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838949.064, "dur": 1.318, + "args": { + "External id": 1445838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838949.563, "dur": 0.744, + "args": { + "External id": 1445839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838954.766, "dur": 6.154, + "args": { + "External id": 1445840,"Record function id": 0, "Ev Idx": 11215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838955.985, "dur": 4.523, + "args": { + "External id": 1445841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838956.457, "dur": 3.511, + "args": { + "External id": 1445842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838957.043, "dur": 2.864, + "args": { + "External id": 1445843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838964.444, "dur": 4.353, + "args": { + "External id": 1445844,"Record function id": 0, "Ev Idx": 11219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838965.586, "dur": 2.769, + "args": { + "External id": 1445845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838966.176, "dur": 1.622, + "args": { + "External id": 1445846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838966.620, "dur": 1.017, + "args": { + "External id": 1445847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838972.466, "dur": 4.065, + "args": { + "External id": 1445848,"Record function id": 0, "Ev Idx": 11223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855838973.559, "dur": 2.520, + "args": { + "External id": 1445849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838974.019, "dur": 1.371, + "args": { + "External id": 1445850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855838974.475, "dur": 0.811, + "args": { + "External id": 1445851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855839000.658, "dur": 7.014, + "args": { + "External id": 1445852,"Record function id": 0, "Ev Idx": 11227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855839002.491, "dur": 4.515, + "args": { + "External id": 1445853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855839003.713, "dur": 2.418, + "args": { + "External id": 1445854,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855839004.396, "dur": 1.541, + "args": { + "External id": 1445855,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855839012.750, "dur": 65287.715, + "args": { + "External id": 1445856,"Record function id": 0, "Sequence number": 15348894, "Fwd thread id": 1, "Ev Idx": 11231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855839014.284, "dur": 65276.630, + "args": { + "External id": 1445857,"Sequence number": 15348894, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11232 + } + }, + { + "ph": "f", "id": 441, "pid": 2338706, "tid": 2379422, "ts": 6413855839014.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413855839045.634, "dur": 73.253, + "args": { + "External id": 1445858,"Record function id": 0, "Ev Idx": 11233 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413855839128.122, "dur": 70.138, + "args": { + "External id": 1445859,"Record function id": 0, "Ev Idx": 11234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 2338706, "tid": 2379422, + "ts": 6413855839204.400, "dur": 65078.181, + "args": { + "External id": 1445860,"Record function id": 0, "Ev Idx": 11235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855839298.574, "dur": 7.042, + "args": { + "External id": 1445861,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855839315.762, "dur": 8.165, + "args": { + "External id": 1445862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855839338.566, "dur": 63905.354, + "args": { + "External id": 1445863,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855839352.762, "dur": 63878.043, + "args": { + "External id": 1445864,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855839459.152, "dur": 17.667, + "args": { + "External id": 1445865,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855839496.345, "dur": 63688.694, + "args": { + "External id": 1445866,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855839499.225, "dur": 63684.752, + "args": { + "External id": 1445867,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855839503.820, "dur": 8.344, + "args": { + "External id": 1445868,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855839514.437, "dur": 63664.181, + "args": { + "External id": 1445869,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855903356.278, "dur": 12.456, + "args": { + "External id": 1445870,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855903359.704, "dur": 8.644, + "args": { + "External id": 1445871,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855903399.782, "dur": 377.835, + "args": { + "External id": 1445872,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855903431.206, "dur": 341.480, + "args": { + "External id": 1445873,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11248, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855903443.263, "dur": 324.368, + "args": { + "External id": 1445874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855903796.348, "dur": 2.459, + "args": { + "External id": 1445875,"Record function id": 0, "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": 11250, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855903856.204, "dur": 6.465, + "args": { + "External id": 1445876,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855903874.826, "dur": 32.928, + "args": { + "External id": 1445877,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855903918.113, "dur": 1.798, + "args": { + "External id": 1445878,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855903925.645, "dur": 12.614, + "args": { + "External id": 1445879,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855903944.102, "dur": 3.044, + "args": { + "External id": 1445880,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855903951.702, "dur": 12.391, + "args": { + "External id": 1445881,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904007.586, "dur": 2.332, + "args": { + "External id": 1445882,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904016.913, "dur": 15.003, + "args": { + "External id": 1445883,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904038.464, "dur": 0.868, + "args": { + "External id": 1445884,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904043.271, "dur": 42.762, + "args": { + "External id": 1445885,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904094.208, "dur": 1.338, + "args": { + "External id": 1445886,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904100.418, "dur": 12.634, + "args": { + "External id": 1445887,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904119.803, "dur": 0.895, + "args": { + "External id": 1445888,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904159.754, "dur": 12.388, + "args": { + "External id": 1445889,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904180.400, "dur": 1.097, + "args": { + "External id": 1445890,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904186.728, "dur": 10.463, + "args": { + "External id": 1445891,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904201.663, "dur": 0.705, + "args": { + "External id": 1445892,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904206.631, "dur": 10.982, + "args": { + "External id": 1445893,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855904318.357, "dur": 2918.109, + "args": { + "External id": 1445894,"Record function id": 0, "Ev Idx": 11269 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413855904339.576, "dur": 1094.941, + "args": { + "External id": 1445895,"Record function id": 0, "Ev Idx": 11270 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413855904354.362, "dur": 325.027, + "args": { + "External id": 1445896,"Record function id": 0, "Ev Idx": 11271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904450.975, "dur": 4.507, + "args": { + "External id": 1445897,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904459.065, "dur": 3.199, + "args": { + "External id": 1445898,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904464.337, "dur": 0.765, + "args": { + "External id": 1445899,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904468.924, "dur": 0.767, + "args": { + "External id": 1445900,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904470.964, "dur": 0.936, + "args": { + "External id": 1445901,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904473.196, "dur": 0.740, + "args": { + "External id": 1445902,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904476.142, "dur": 0.732, + "args": { + "External id": 1445903,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904479.511, "dur": 1.988, + "args": { + "External id": 1445904,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904482.773, "dur": 0.725, + "args": { + "External id": 1445905,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855904485.084, "dur": 2.616, + "args": { + "External id": 1445906,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855904505.901, "dur": 144.376, + "args": { + "External id": 1445907,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855904523.357, "dur": 122.184, + "args": { + "External id": 1445908,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855904539.596, "dur": 14.715, + "args": { + "External id": 1445909,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855904558.073, "dur": 60.923, + "args": { + "External id": 1445910,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855904562.672, "dur": 55.995, + "args": { + "External id": 1445911,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904566.498, "dur": 5.310, + "args": { + "External id": 1445912,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904573.362, "dur": 44.790, + "args": { + "External id": 1445913,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11288 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 2338706, "tid": 2379422, + "ts": 6413855904770.699, "dur": 656.146, + "args": { + "External id": 1445914,"Record function id": 0, "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413855904786.934, "dur": 627.052, + "args": { + "External id": 1445915,"Record function id": 0, "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855904849.897, "dur": 4.517, + "args": { + "External id": 1445916,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855904869.552, "dur": 28.303, + "args": { + "External id": 1445917,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904874.754, "dur": 1.251, + "args": { + "External id": 1445918,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904877.866, "dur": 0.523, + "args": { + "External id": 1445919,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904880.187, "dur": 0.489, + "args": { + "External id": 1445920,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904882.222, "dur": 0.414, + "args": { + "External id": 1445921,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904883.978, "dur": 2.811, + "args": { + "External id": 1445922,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904888.034, "dur": 0.337, + "args": { + "External id": 1445923,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904890.041, "dur": 0.578, + "args": { + "External id": 1445924,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904891.763, "dur": 0.562, + "args": { + "External id": 1445925,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855904893.745, "dur": 0.627, + "args": { + "External id": 1445926,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855904909.035, "dur": 39.927, + "args": { + "External id": 1445927,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855904997.566, "dur": 155.958, + "args": { + "External id": 1445928,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 11303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855905010.527, "dur": 4.765, + "args": { + "External id": 1445929,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855905020.866, "dur": 10.792, + "args": { + "External id": 1445930,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855905025.198, "dur": 6.023, + "args": { + "External id": 1445931,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 11306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905028.957, "dur": 0.735, + "args": { + "External id": 1445932,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855905038.918, "dur": 57.052, + "args": { + "External id": 1445933,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905041.085, "dur": 0.319, + "args": { + "External id": 1445934,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905042.595, "dur": 2.792, + "args": { + "External id": 1445935,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905046.955, "dur": 0.317, + "args": { + "External id": 1445936,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905048.814, "dur": 0.270, + "args": { + "External id": 1445937,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905050.257, "dur": 0.492, + "args": { + "External id": 1445938,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905052.276, "dur": 32.882, + "args": { + "External id": 1445939,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905088.623, "dur": 0.532, + "args": { + "External id": 1445940,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905090.452, "dur": 0.304, + "args": { + "External id": 1445941,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855905092.352, "dur": 0.496, + "args": { + "External id": 1445942,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855905108.683, "dur": 34.082, + "args": { + "External id": 1445943,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855905220.815, "dur": 118.958, + "args": { + "External id": 1445944,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 11319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855905248.764, "dur": 87.508, + "args": { + "External id": 1445945,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11320, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855905260.145, "dur": 71.897, + "args": { + "External id": 1445946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 11321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855905355.772, "dur": 2.014, + "args": { + "External id": 1445947,"Record function id": 0, "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": 11322, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855905442.322, "dur": 1771.246, + "args": { + "External id": 1445948,"Sequence number": 15348893, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11323 + } + }, + { + "ph": "f", "id": 442, "pid": 2338706, "tid": 2379422, "ts": 6413855905442.322, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855905555.966, "dur": 105.327, + "args": { + "External id": 1445949,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855905703.283, "dur": 43.532, + "args": { + "External id": 1445950,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855905766.306, "dur": 47.590, + "args": { + "External id": 1445951,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855905823.289, "dur": 30.576, + "args": { + "External id": 1445952,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855905860.083, "dur": 38.427, + "args": { + "External id": 1445953,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855905904.902, "dur": 27.162, + "args": { + "External id": 1445954,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855905941.437, "dur": 29.669, + "args": { + "External id": 1445955,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855906019.010, "dur": 28.166, + "args": { + "External id": 1445956,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855906105.811, "dur": 34.406, + "args": { + "External id": 1445957,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855906167.118, "dur": 20.953, + "args": { + "External id": 1445958,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855906201.906, "dur": 16.321, + "args": { + "External id": 1445959,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906228.497, "dur": 45.383, + "args": { + "External id": 1445960,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906277.614, "dur": 33.903, + "args": { + "External id": 1445961,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855906340.241, "dur": 245.294, + "args": { + "External id": 1445962,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855906416.390, "dur": 6.534, + "args": { + "External id": 1445963,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855906424.818, "dur": 2.870, + "args": { + "External id": 1445964,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855906428.894, "dur": 2.368, + "args": { + "External id": 1445965,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855906432.207, "dur": 4.501, + "args": { + "External id": 1445966,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855906482.609, "dur": 5.006, + "args": { + "External id": 1445967,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855906484.660, "dur": 2.811, + "args": { + "External id": 1445968,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855906489.484, "dur": 32.950, + "args": { + "External id": 1445969,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855906494.867, "dur": 1.642, + "args": { + "External id": 1445970,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855906523.840, "dur": 1.291, + "args": { + "External id": 1445971,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855906524.528, "dur": 0.495, + "args": { + "External id": 1445972,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855906526.243, "dur": 16.293, + "args": { + "External id": 1445973,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855906528.360, "dur": 0.449, + "args": { + "External id": 1445974,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855906620.398, "dur": 25.653, + "args": { + "External id": 1445975,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855906660.787, "dur": 18.238, + "args": { + "External id": 1445976,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906686.381, "dur": 37.019, + "args": { + "External id": 1445977,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906730.200, "dur": 36.465, + "args": { + "External id": 1445978,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906774.494, "dur": 20.297, + "args": { + "External id": 1445979,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906803.209, "dur": 45.652, + "args": { + "External id": 1445980,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906863.740, "dur": 36.239, + "args": { + "External id": 1445981,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855906907.060, "dur": 31.843, + "args": { + "External id": 1445982,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855906956.549, "dur": 46.445, + "args": { + "External id": 1445983,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855907023.885, "dur": 25.574, + "args": { + "External id": 1445984,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855907098.197, "dur": 22.255, + "args": { + "External id": 1445985,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855907136.134, "dur": 15.661, + "args": { + "External id": 1445986,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855907164.112, "dur": 16.740, + "args": { + "External id": 1445987,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907260.082, "dur": 15.942, + "args": { + "External id": 1445988,"Record function id": 0, "Ev Idx": 11363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907263.617, "dur": 11.595, + "args": { + "External id": 1445989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907267.995, "dur": 5.874, + "args": { + "External id": 1445990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907269.661, "dur": 4.059, + "args": { + "External id": 1445991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907280.098, "dur": 5.669, + "args": { + "External id": 1445992,"Record function id": 0, "Ev Idx": 11367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907281.702, "dur": 3.610, + "args": { + "External id": 1445993,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907282.808, "dur": 1.887, + "args": { + "External id": 1445994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907283.605, "dur": 0.992, + "args": { + "External id": 1445995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907288.982, "dur": 4.587, + "args": { + "External id": 1445996,"Record function id": 0, "Ev Idx": 11371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907290.439, "dur": 2.733, + "args": { + "External id": 1445997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907291.362, "dur": 1.374, + "args": { + "External id": 1445998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907291.895, "dur": 0.751, + "args": { + "External id": 1445999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907296.691, "dur": 4.068, + "args": { + "External id": 1446000,"Record function id": 0, "Ev Idx": 11375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907297.918, "dur": 2.426, + "args": { + "External id": 1446001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907298.705, "dur": 1.209, + "args": { + "External id": 1446002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907299.074, "dur": 0.775, + "args": { + "External id": 1446003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907313.686, "dur": 4.307, + "args": { + "External id": 1446004,"Record function id": 0, "Ev Idx": 11379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907314.840, "dur": 2.732, + "args": { + "External id": 1446005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907315.692, "dur": 1.286, + "args": { + "External id": 1446006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907315.976, "dur": 0.927, + "args": { + "External id": 1446007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907321.083, "dur": 6.605, + "args": { + "External id": 1446008,"Record function id": 0, "Ev Idx": 11383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907322.170, "dur": 5.110, + "args": { + "External id": 1446009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907322.818, "dur": 3.857, + "args": { + "External id": 1446010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907323.204, "dur": 3.401, + "args": { + "External id": 1446011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907331.443, "dur": 4.031, + "args": { + "External id": 1446012,"Record function id": 0, "Ev Idx": 11387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907332.401, "dur": 2.662, + "args": { + "External id": 1446013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907333.174, "dur": 1.389, + "args": { + "External id": 1446014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907333.470, "dur": 1.031, + "args": { + "External id": 1446015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907338.856, "dur": 3.639, + "args": { + "External id": 1446016,"Record function id": 0, "Ev Idx": 11391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907339.930, "dur": 2.133, + "args": { + "External id": 1446017,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907340.493, "dur": 1.043, + "args": { + "External id": 1446018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907340.902, "dur": 0.570, + "args": { + "External id": 1446019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907345.910, "dur": 3.486, + "args": { + "External id": 1446020,"Record function id": 0, "Ev Idx": 11395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855907346.787, "dur": 2.233, + "args": { + "External id": 1446021,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907347.415, "dur": 1.041, + "args": { + "External id": 1446022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855907347.739, "dur": 0.640, + "args": { + "External id": 1446023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855907353.809, "dur": 64280.433, + "args": { + "External id": 1446024,"Record function id": 0, "Sequence number": 15348892, "Fwd thread id": 1, "Ev Idx": 11399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855907355.030, "dur": 64269.203, + "args": { + "External id": 1446025,"Sequence number": 15348892, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11400 + } + }, + { + "ph": "f", "id": 443, "pid": 2338706, "tid": 2379422, "ts": 6413855907355.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413855907385.049, "dur": 36.916, + "args": { + "External id": 1446026,"Record function id": 0, "Ev Idx": 11401 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413855907429.678, "dur": 68.903, + "args": { + "External id": 1446027,"Record function id": 0, "Ev Idx": 11402 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 2338706, "tid": 2379422, + "ts": 6413855907504.565, "dur": 64111.753, + "args": { + "External id": 1446028,"Record function id": 0, "Ev Idx": 11403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855907592.599, "dur": 6.964, + "args": { + "External id": 1446029,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855907609.151, "dur": 4.551, + "args": { + "External id": 1446030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855907627.473, "dur": 63017.658, + "args": { + "External id": 1446031,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855907641.026, "dur": 62990.015, + "args": { + "External id": 1446032,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855907816.140, "dur": 19.424, + "args": { + "External id": 1446033,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855907856.921, "dur": 62729.229, + "args": { + "External id": 1446034,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855907859.661, "dur": 62725.407, + "args": { + "External id": 1446035,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855907864.330, "dur": 9.118, + "args": { + "External id": 1446036,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855907875.610, "dur": 62704.488, + "args": { + "External id": 1446037,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855970757.919, "dur": 12.858, + "args": { + "External id": 1446038,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855970761.588, "dur": 8.828, + "args": { + "External id": 1446039,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855970803.556, "dur": 433.552, + "args": { + "External id": 1446040,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855970834.126, "dur": 397.286, + "args": { + "External id": 1446041,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11416, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855970845.703, "dur": 379.763, + "args": { + "External id": 1446042,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855971258.566, "dur": 2.243, + "args": { + "External id": 1446043,"Record function id": 0, "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": 11418, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971324.874, "dur": 6.819, + "args": { + "External id": 1446044,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971344.137, "dur": 39.092, + "args": { + "External id": 1446045,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971393.915, "dur": 3.285, + "args": { + "External id": 1446046,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971403.634, "dur": 11.960, + "args": { + "External id": 1446047,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971421.482, "dur": 0.769, + "args": { + "External id": 1446048,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971426.733, "dur": 11.233, + "args": { + "External id": 1446049,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971442.216, "dur": 0.907, + "args": { + "External id": 1446050,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971447.689, "dur": 9.678, + "args": { + "External id": 1446051,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971461.666, "dur": 0.915, + "args": { + "External id": 1446052,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971467.210, "dur": 10.982, + "args": { + "External id": 1446053,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971482.145, "dur": 0.925, + "args": { + "External id": 1446054,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971487.435, "dur": 10.039, + "args": { + "External id": 1446055,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971502.266, "dur": 0.909, + "args": { + "External id": 1446056,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971507.574, "dur": 10.334, + "args": { + "External id": 1446057,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971521.986, "dur": 0.788, + "args": { + "External id": 1446058,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971527.189, "dur": 9.929, + "args": { + "External id": 1446059,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971541.231, "dur": 0.767, + "args": { + "External id": 1446060,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971545.860, "dur": 10.822, + "args": { + "External id": 1446061,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855971648.987, "dur": 2951.482, + "args": { + "External id": 1446062,"Record function id": 0, "Ev Idx": 11437 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413855971671.543, "dur": 1101.532, + "args": { + "External id": 1446063,"Record function id": 0, "Ev Idx": 11438 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413855971690.046, "dur": 347.196, + "args": { + "External id": 1446064,"Record function id": 0, "Ev Idx": 11439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971778.276, "dur": 6.104, + "args": { + "External id": 1446065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971787.447, "dur": 0.910, + "args": { + "External id": 1446066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971791.624, "dur": 0.843, + "args": { + "External id": 1446067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971794.180, "dur": 0.650, + "args": { + "External id": 1446068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971796.419, "dur": 0.998, + "args": { + "External id": 1446069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971798.919, "dur": 0.666, + "args": { + "External id": 1446070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971802.182, "dur": 1.163, + "args": { + "External id": 1446071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971804.926, "dur": 1.965, + "args": { + "External id": 1446072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971808.238, "dur": 2.918, + "args": { + "External id": 1446073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855971812.582, "dur": 0.702, + "args": { + "External id": 1446074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855971839.871, "dur": 160.933, + "args": { + "External id": 1446075,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855971856.964, "dur": 119.950, + "args": { + "External id": 1446076,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855971871.567, "dur": 15.192, + "args": { + "External id": 1446077,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855971890.511, "dur": 60.519, + "args": { + "External id": 1446078,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855971893.395, "dur": 57.331, + "args": { + "External id": 1446079,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855971897.085, "dur": 5.342, + "args": { + "External id": 1446080,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855971904.531, "dur": 45.434, + "args": { + "External id": 1446081,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11456 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 2338706, "tid": 2379422, + "ts": 6413855972175.740, "dur": 589.932, + "args": { + "External id": 1446082,"Record function id": 0, "Ev Idx": 11457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413855972194.087, "dur": 559.014, + "args": { + "External id": 1446083,"Record function id": 0, "Ev Idx": 11458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855972263.088, "dur": 6.354, + "args": { + "External id": 1446084,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855972285.905, "dur": 29.866, + "args": { + "External id": 1446085,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972291.613, "dur": 1.755, + "args": { + "External id": 1446086,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972295.246, "dur": 0.609, + "args": { + "External id": 1446087,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972297.462, "dur": 0.497, + "args": { + "External id": 1446088,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972299.750, "dur": 2.500, + "args": { + "External id": 1446089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972303.598, "dur": 0.507, + "args": { + "External id": 1446090,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972305.892, "dur": 0.379, + "args": { + "External id": 1446091,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972307.785, "dur": 0.430, + "args": { + "External id": 1446092,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972309.370, "dur": 0.329, + "args": { + "External id": 1446093,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972311.381, "dur": 0.275, + "args": { + "External id": 1446094,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855972326.583, "dur": 43.115, + "args": { + "External id": 1446095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2379422, + "ts": 6413855972399.762, "dur": 123.095, + "args": { + "External id": 1446096,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 11471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855972410.452, "dur": 3.050, + "args": { + "External id": 1446097,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2379422, + "ts": 6413855972418.597, "dur": 10.403, + "args": { + "External id": 1446098,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2379422, + "ts": 6413855972423.028, "dur": 5.551, + "args": { + "External id": 1446099,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 11474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972426.783, "dur": 0.598, + "args": { + "External id": 1446100,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 11475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2379422, + "ts": 6413855972435.201, "dur": 24.247, + "args": { + "External id": 1446101,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 11476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972437.016, "dur": 2.712, + "args": { + "External id": 1446102,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972440.883, "dur": 0.629, + "args": { + "External id": 1446103,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972443.454, "dur": 0.338, + "args": { + "External id": 1446104,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972445.595, "dur": 0.415, + "args": { + "External id": 1446105,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972447.328, "dur": 0.375, + "args": { + "External id": 1446106,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972449.199, "dur": 0.331, + "args": { + "External id": 1446107,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972451.078, "dur": 0.373, + "args": { + "External id": 1446108,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972452.411, "dur": 0.262, + "args": { + "External id": 1446109,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855972454.698, "dur": 2.338, + "args": { + "External id": 1446110,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855972486.360, "dur": 28.813, + "args": { + "External id": 1446111,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 11486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413855972567.732, "dur": 114.972, + "args": { + "External id": 1446112,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 11487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855972594.198, "dur": 85.272, + "args": { + "External id": 1446113,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11488, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2379422, + "ts": 6413855972604.417, "dur": 70.720, + "args": { + "External id": 1446114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 11489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413855972699.292, "dur": 1.913, + "args": { + "External id": 1446115,"Record function id": 0, "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": 11490, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855972780.539, "dur": 1796.532, + "args": { + "External id": 1446116,"Sequence number": 15348891, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11491 + } + }, + { + "ph": "f", "id": 444, "pid": 2338706, "tid": 2379422, "ts": 6413855972780.539, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855972892.606, "dur": 125.017, + "args": { + "External id": 1446117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855973098.544, "dur": 47.059, + "args": { + "External id": 1446118,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973168.648, "dur": 59.221, + "args": { + "External id": 1446119,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973238.005, "dur": 32.471, + "args": { + "External id": 1446120,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973277.231, "dur": 32.186, + "args": { + "External id": 1446121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973316.076, "dur": 27.002, + "args": { + "External id": 1446122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973351.700, "dur": 29.116, + "args": { + "External id": 1446123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855973408.617, "dur": 24.896, + "args": { + "External id": 1446124,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413855973452.447, "dur": 29.380, + "args": { + "External id": 1446125,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855973504.629, "dur": 18.996, + "args": { + "External id": 1446126,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855973537.118, "dur": 14.835, + "args": { + "External id": 1446127,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973562.665, "dur": 36.924, + "args": { + "External id": 1446128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855973603.107, "dur": 33.240, + "args": { + "External id": 1446129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413855973664.892, "dur": 245.362, + "args": { + "External id": 1446130,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855973745.554, "dur": 6.452, + "args": { + "External id": 1446131,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855973754.227, "dur": 2.954, + "args": { + "External id": 1446132,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855973758.425, "dur": 2.271, + "args": { + "External id": 1446133,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855973762.011, "dur": 4.822, + "args": { + "External id": 1446134,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855973810.772, "dur": 5.357, + "args": { + "External id": 1446135,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855973813.122, "dur": 2.855, + "args": { + "External id": 1446136,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855973817.838, "dur": 31.243, + "args": { + "External id": 1446137,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855973823.574, "dur": 1.790, + "args": { + "External id": 1446138,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413855973850.454, "dur": 1.561, + "args": { + "External id": 1446139,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855973851.296, "dur": 0.636, + "args": { + "External id": 1446140,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413855973853.349, "dur": 14.423, + "args": { + "External id": 1446141,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855973855.507, "dur": 0.548, + "args": { + "External id": 1446142,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413855973944.475, "dur": 25.441, + "args": { + "External id": 1446143,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855974007.686, "dur": 18.862, + "args": { + "External id": 1446144,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855974036.258, "dur": 82.647, + "args": { + "External id": 1446145,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855974129.338, "dur": 42.340, + "args": { + "External id": 1446146,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855974183.921, "dur": 22.188, + "args": { + "External id": 1446147,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855974212.363, "dur": 50.716, + "args": { + "External id": 1446148,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855974282.349, "dur": 34.052, + "args": { + "External id": 1446149,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413855974324.716, "dur": 33.915, + "args": { + "External id": 1446150,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413855974379.835, "dur": 26.921, + "args": { + "External id": 1446151,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855974421.801, "dur": 29.618, + "args": { + "External id": 1446152,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413855974465.399, "dur": 18.516, + "args": { + "External id": 1446153,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413855974499.786, "dur": 15.284, + "args": { + "External id": 1446154,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413855974527.624, "dur": 17.453, + "args": { + "External id": 1446155,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974623.638, "dur": 16.012, + "args": { + "External id": 1446156,"Record function id": 0, "Ev Idx": 11531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974627.213, "dur": 11.483, + "args": { + "External id": 1446157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974631.666, "dur": 6.203, + "args": { + "External id": 1446158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974633.519, "dur": 4.198, + "args": { + "External id": 1446159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974643.601, "dur": 5.585, + "args": { + "External id": 1446160,"Record function id": 0, "Ev Idx": 11535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974645.397, "dur": 3.285, + "args": { + "External id": 1446161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974646.190, "dur": 1.957, + "args": { + "External id": 1446162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974647.111, "dur": 0.942, + "args": { + "External id": 1446163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974652.578, "dur": 5.048, + "args": { + "External id": 1446164,"Record function id": 0, "Ev Idx": 11539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974654.260, "dur": 2.784, + "args": { + "External id": 1446165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974654.807, "dur": 1.574, + "args": { + "External id": 1446166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974655.490, "dur": 0.757, + "args": { + "External id": 1446167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974660.762, "dur": 4.259, + "args": { + "External id": 1446168,"Record function id": 0, "Ev Idx": 11543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974661.813, "dur": 2.763, + "args": { + "External id": 1446169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974662.304, "dur": 1.573, + "args": { + "External id": 1446170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974662.816, "dur": 0.986, + "args": { + "External id": 1446171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974668.102, "dur": 4.335, + "args": { + "External id": 1446172,"Record function id": 0, "Ev Idx": 11547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974669.370, "dur": 2.658, + "args": { + "External id": 1446173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974669.861, "dur": 1.537, + "args": { + "External id": 1446174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974670.416, "dur": 0.915, + "args": { + "External id": 1446175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974675.619, "dur": 5.758, + "args": { + "External id": 1446176,"Record function id": 0, "Ev Idx": 11551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974676.703, "dur": 4.245, + "args": { + "External id": 1446177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974677.281, "dur": 3.243, + "args": { + "External id": 1446178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974677.571, "dur": 2.891, + "args": { + "External id": 1446179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974684.535, "dur": 4.248, + "args": { + "External id": 1446180,"Record function id": 0, "Ev Idx": 11555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974686.245, "dur": 2.137, + "args": { + "External id": 1446181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974686.718, "dur": 1.211, + "args": { + "External id": 1446182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974687.069, "dur": 0.791, + "args": { + "External id": 1446183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974692.215, "dur": 4.452, + "args": { + "External id": 1446184,"Record function id": 0, "Ev Idx": 11559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974693.488, "dur": 2.720, + "args": { + "External id": 1446185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974694.050, "dur": 1.513, + "args": { + "External id": 1446186,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974694.586, "dur": 0.866, + "args": { + "External id": 1446187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974699.792, "dur": 4.743, + "args": { + "External id": 1446188,"Record function id": 0, "Ev Idx": 11563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413855974701.408, "dur": 2.678, + "args": { + "External id": 1446189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974702.051, "dur": 1.504, + "args": { + "External id": 1446190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413855974702.897, "dur": 0.593, + "args": { + "External id": 1446191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855974708.682, "dur": 66413.832, + "args": { + "External id": 1446192,"Record function id": 0, "Sequence number": 15348890, "Fwd thread id": 1, "Ev Idx": 11567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413855974710.117, "dur": 66400.429, + "args": { + "External id": 1446193,"Sequence number": 15348890, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11568 + } + }, + { + "ph": "f", "id": 445, "pid": 2338706, "tid": 2379422, "ts": 6413855974710.117, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413855974740.779, "dur": 40.251, + "args": { + "External id": 1446194,"Record function id": 0, "Ev Idx": 11569 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413855974788.984, "dur": 70.880, + "args": { + "External id": 1446195,"Record function id": 0, "Ev Idx": 11570 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 2338706, "tid": 2379422, + "ts": 6413855974865.613, "dur": 66235.214, + "args": { + "External id": 1446196,"Record function id": 0, "Ev Idx": 11571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855974955.454, "dur": 7.026, + "args": { + "External id": 1446197,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413855974972.031, "dur": 4.408, + "args": { + "External id": 1446198,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855975012.867, "dur": 65033.382, + "args": { + "External id": 1446199,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413855975028.031, "dur": 65003.887, + "args": { + "External id": 1446200,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413855975219.740, "dur": 21.563, + "args": { + "External id": 1446201,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413855975262.058, "dur": 64710.297, + "args": { + "External id": 1446202,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413855975265.245, "dur": 64706.039, + "args": { + "External id": 1446203,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413855975269.634, "dur": 11.517, + "args": { + "External id": 1446204,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413855975283.424, "dur": 64682.493, + "args": { + "External id": 1446205,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856040186.378, "dur": 13.597, + "args": { + "External id": 1446206,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856040190.017, "dur": 9.418, + "args": { + "External id": 1446207,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040233.791, "dur": 411.027, + "args": { + "External id": 1446208,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413856040261.304, "dur": 378.145, + "args": { + "External id": 1446209,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11584, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413856040273.933, "dur": 360.371, + "args": { + "External id": 1446210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413856040667.227, "dur": 2.306, + "args": { + "External id": 1446211,"Record function id": 0, "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": 11586, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040733.180, "dur": 6.939, + "args": { + "External id": 1446212,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040753.124, "dur": 34.952, + "args": { + "External id": 1446213,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040798.299, "dur": 1.874, + "args": { + "External id": 1446214,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040813.112, "dur": 12.192, + "args": { + "External id": 1446215,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040831.115, "dur": 1.043, + "args": { + "External id": 1446216,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040836.799, "dur": 10.737, + "args": { + "External id": 1446217,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040853.523, "dur": 0.957, + "args": { + "External id": 1446218,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040859.135, "dur": 10.464, + "args": { + "External id": 1446219,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040874.126, "dur": 2.828, + "args": { + "External id": 1446220,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040881.312, "dur": 20.706, + "args": { + "External id": 1446221,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040905.925, "dur": 1.089, + "args": { + "External id": 1446222,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040911.161, "dur": 10.302, + "args": { + "External id": 1446223,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040927.456, "dur": 0.638, + "args": { + "External id": 1446224,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040932.021, "dur": 10.415, + "args": { + "External id": 1446225,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040946.307, "dur": 0.934, + "args": { + "External id": 1446226,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040951.253, "dur": 9.697, + "args": { + "External id": 1446227,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856040965.136, "dur": 1.007, + "args": { + "External id": 1446228,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856040970.387, "dur": 30.510, + "args": { + "External id": 1446229,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413856041140.508, "dur": 2291.260, + "args": { + "External id": 1446230,"Record function id": 0, "Ev Idx": 11605 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413856041163.822, "dur": 457.902, + "args": { + "External id": 1446231,"Record function id": 0, "Ev Idx": 11606 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413856041180.888, "dur": 335.488, + "args": { + "External id": 1446232,"Record function id": 0, "Ev Idx": 11607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041278.850, "dur": 4.534, + "args": { + "External id": 1446233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041287.062, "dur": 1.387, + "args": { + "External id": 1446234,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041290.169, "dur": 0.983, + "args": { + "External id": 1446235,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041293.229, "dur": 3.172, + "args": { + "External id": 1446236,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041298.161, "dur": 1.114, + "args": { + "External id": 1446237,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041302.043, "dur": 0.962, + "args": { + "External id": 1446238,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041304.604, "dur": 0.873, + "args": { + "External id": 1446239,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041306.646, "dur": 2.084, + "args": { + "External id": 1446240,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041310.804, "dur": 0.935, + "args": { + "External id": 1446241,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856041314.886, "dur": 0.715, + "args": { + "External id": 1446242,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 11617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413856041334.302, "dur": 151.429, + "args": { + "External id": 1446243,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413856041351.834, "dur": 129.278, + "args": { + "External id": 1446244,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 11619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856041367.299, "dur": 14.727, + "args": { + "External id": 1446245,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413856041385.830, "dur": 67.119, + "args": { + "External id": 1446246,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 11621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413856041388.661, "dur": 63.983, + "args": { + "External id": 1446247,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 11622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856041392.515, "dur": 8.335, + "args": { + "External id": 1446248,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413856041402.648, "dur": 49.508, + "args": { + "External id": 1446249,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 11624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413856041629.737, "dur": 1776.210, + "args": { + "External id": 1446250,"Sequence number": 15348889, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11625 + } + }, + { + "ph": "f", "id": 446, "pid": 2338706, "tid": 2379422, "ts": 6413856041629.737, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856041742.884, "dur": 102.754, + "args": { + "External id": 1446251,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [14336, 1], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 11626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 2338706, "tid": 2379422, + "ts": 6413856041884.673, "dur": 40.804, + "args": { + "External id": 1446252,"kernel_hash": "cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/uw/cuwopwt4ur7jv5ehxyphohnjewkwckjorwzrlc2qu5z3edn3777m.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [32768, 14336], [8, 4096, 14336], [8, 4096, 14336], [8, 4096, 14336], []], "Ev Idx": 11627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 2338706, "tid": 2379422, + "ts": 6413856041945.304, "dur": 66.756, + "args": { + "External id": 1446253,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 4096], [0, 14336, 1], [58720256, 14336, 1]], "Input Dims": [[1, 4096, 32768], [1, 32768, 14336], [1, 4096, 14336]], "Ev Idx": 11628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042042.841, "dur": 74.514, + "args": { + "External id": 1446254,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042129.327, "dur": 36.228, + "args": { + "External id": 1446255,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042173.480, "dur": 28.452, + "args": { + "External id": 1446256,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 14336], [4096, 1], [4096, 1]], "Input Dims": [[14336, 32768], [32768, 4096], [14336, 4096]], "Ev Idx": 11631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042212.696, "dur": 31.324, + "args": { + "External id": 1446257,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 11632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 2338706, "tid": 2379422, + "ts": 6413856042270.285, "dur": 29.568, + "args": { + "External id": 1446258,"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": [[4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 11633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338706, "tid": 2379422, + "ts": 6413856042318.114, "dur": 31.518, + "args": { + "External id": 1446259,"kernel_hash": "cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/q2/cq2rd45bzuewzky5ru3epoa4jgdm2eh637bwzg2y3olumezvi2hx.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413856042371.818, "dur": 20.449, + "args": { + "External id": 1446260,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413856042406.212, "dur": 17.214, + "args": { + "External id": 1446261,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042434.560, "dur": 37.097, + "args": { + "External id": 1446262,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042475.710, "dur": 32.512, + "args": { + "External id": 1446263,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 2338706, "tid": 2379422, + "ts": 6413856042537.849, "dur": 250.625, + "args": { + "External id": 1446264,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[16777216, 4096, 128, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [16777216, 4096, 128, 1], [131072, 4096, 1], [16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [8, 4096, 32, 128], [8, 32, 4096], [8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 11639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856042618.991, "dur": 6.562, + "args": { + "External id": 1446265,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856042627.681, "dur": 2.806, + "args": { + "External id": 1446266,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856042631.758, "dur": 2.790, + "args": { + "External id": 1446267,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856042635.587, "dur": 4.814, + "args": { + "External id": 1446268,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413856042684.523, "dur": 5.006, + "args": { + "External id": 1446269,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856042686.392, "dur": 2.917, + "args": { + "External id": 1446270,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413856042691.496, "dur": 30.896, + "args": { + "External id": 1446271,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856042697.280, "dur": 1.671, + "args": { + "External id": 1446272,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2379422, + "ts": 6413856042724.058, "dur": 1.583, + "args": { + "External id": 1446273,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856042725.041, "dur": 0.515, + "args": { + "External id": 1446274,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 4, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 11649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2379422, + "ts": 6413856042726.554, "dur": 14.966, + "args": { + "External id": 1446275,"Record function id": 0, "Concrete Inputs": ["", "[3]", "False", "", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 512, 128, 1], [], [], [], [4194304, 1024, 128, 1]], "Input Dims": [[8, 4096, 8, 4, 128], [], [], [], [8, 4096, 8, 128]], "Ev Idx": 11650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856042729.449, "dur": 0.637, + "args": { + "External id": 1446276,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 1, 128]", "[4194304, 1024, 128, 0, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], []], "Ev Idx": 11651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2379422, + "ts": 6413856042824.868, "dur": 29.188, + "args": { + "External id": 1446277,"kernel_hash": "cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/vl/cvl6m5botwvmbpqmwk6qhxr3434sm2t3rah42nj7xsdba5m7ab2o.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2379422, + "ts": 6413856042869.856, "dur": 17.096, + "args": { + "External id": 1446278,"kernel_hash": "cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/yo/cyohbdnrtrefnjluve25jrbzkn5nbdd44am66rrsra2mjfxk6odg.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042894.603, "dur": 40.774, + "args": { + "External id": 1446279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856042942.335, "dur": 60.980, + "args": { + "External id": 1446280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856043017.381, "dur": 26.917, + "args": { + "External id": 1446281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 1024], [4096, 1], [4096, 1]], "Input Dims": [[1024, 32768], [32768, 4096], [1024, 4096]], "Ev Idx": 11656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856043050.754, "dur": 72.209, + "args": { + "External id": 1446282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1024, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 1024], [1024, 4096], [32768, 4096]], "Ev Idx": 11657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856043134.254, "dur": 29.827, + "args": { + "External id": 1446283,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 4096], [4096, 1], [4096, 1]], "Input Dims": [[4096, 32768], [32768, 4096], [4096, 4096]], "Ev Idx": 11658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2379422, + "ts": 6413856043172.091, "dur": 29.984, + "args": { + "External id": 1446284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [4096, 1], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 11659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 2338706, "tid": 2379422, + "ts": 6413856043221.127, "dur": 25.262, + "args": { + "External id": 1446285,"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": [[4096, 1], [4096, 1], [4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [32768, 4096], []], "Ev Idx": 11660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_3", "pid": 2338706, "tid": 2379422, + "ts": 6413856043263.167, "dur": 22.528, + "args": { + "External id": 1446286,"kernel_hash": "cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "32768", "4096", "1", "249", "132", "True", "4096", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/df/cdfatgohdja6cpjscd5ulk47n5ozsecw6vgjqwodg5euk5mmpoix.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [4096], [32768, 4096], [32768, 4096], [132, 4096], [32768], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 2338706, "tid": 2379422, + "ts": 6413856043300.486, "dur": 16.709, + "args": { + "External id": 1446287,"kernel_hash": "ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/tw/ctwj4phgp7e4c7awvtwtgq24cmf75exkour63vmsfhv5kzfdrrt3.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [8192, 1, 4096], [], []], "Input Dims": [[132, 4096], [1, 4096, 2], [], []], "Ev Idx": 11662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 2338706, "tid": 2379422, + "ts": 6413856043330.931, "dur": 13.453, + "args": { + "External id": 1446288,"kernel_hash": "c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/47/c47dbscmmtr2kvomvxfi5h6hqbl4caacaijotzpx47lgoa5vxsmg.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 4096], [4096, 1], [], []], "Input Dims": [[1, 4096, 2], [1, 4096], [], []], "Ev Idx": 11663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 2338706, "tid": 2379422, + "ts": 6413856043356.710, "dur": 15.722, + "args": { + "External id": 1446289,"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": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], [8, 4096, 4096], []], "Ev Idx": 11664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043454.805, "dur": 16.365, + "args": { + "External id": 1446290,"Record function id": 0, "Ev Idx": 11665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043458.699, "dur": 11.414, + "args": { + "External id": 1446291,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043463.339, "dur": 5.802, + "args": { + "External id": 1446292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043464.899, "dur": 4.110, + "args": { + "External id": 1446293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043475.068, "dur": 6.045, + "args": { + "External id": 1446294,"Record function id": 0, "Ev Idx": 11669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043476.490, "dur": 4.120, + "args": { + "External id": 1446295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043477.462, "dur": 2.511, + "args": { + "External id": 1446296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043478.302, "dur": 1.573, + "args": { + "External id": 1446297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043484.396, "dur": 4.467, + "args": { + "External id": 1446298,"Record function id": 0, "Ev Idx": 11673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043486.177, "dur": 2.256, + "args": { + "External id": 1446299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043486.769, "dur": 1.224, + "args": { + "External id": 1446300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043487.173, "dur": 0.736, + "args": { + "External id": 1446301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 11676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043492.126, "dur": 5.285, + "args": { + "External id": 1446302,"Record function id": 0, "Ev Idx": 11677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043493.946, "dur": 3.054, + "args": { + "External id": 1446303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043494.599, "dur": 1.991, + "args": { + "External id": 1446304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043495.631, "dur": 0.893, + "args": { + "External id": 1446305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 11680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043500.532, "dur": 5.038, + "args": { + "External id": 1446306,"Record function id": 0, "Ev Idx": 11681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043502.346, "dur": 2.796, + "args": { + "External id": 1446307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043503.093, "dur": 1.487, + "args": { + "External id": 1446308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043503.534, "dur": 0.974, + "args": { + "External id": 1446309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043508.812, "dur": 4.074, + "args": { + "External id": 1446310,"Record function id": 0, "Ev Idx": 11685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043510.223, "dur": 2.214, + "args": { + "External id": 1446311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043511.013, "dur": 1.026, + "args": { + "External id": 1446312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043511.266, "dur": 0.697, + "args": { + "External id": 1446313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 11688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043516.086, "dur": 6.092, + "args": { + "External id": 1446314,"Record function id": 0, "Ev Idx": 11689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043517.468, "dur": 4.271, + "args": { + "External id": 1446315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043518.109, "dur": 3.230, + "args": { + "External id": 1446316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043518.380, "dur": 2.896, + "args": { + "External id": 1446317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043525.303, "dur": 4.910, + "args": { + "External id": 1446318,"Record function id": 0, "Ev Idx": 11693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043527.219, "dur": 2.528, + "args": { + "External id": 1446319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043527.931, "dur": 1.372, + "args": { + "External id": 1446320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043528.483, "dur": 0.705, + "args": { + "External id": 1446321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 11696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043534.039, "dur": 4.354, + "args": { + "External id": 1446322,"Record function id": 0, "Ev Idx": 11697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856043535.282, "dur": 2.655, + "args": { + "External id": 1446323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043536.229, "dur": 1.228, + "args": { + "External id": 1446324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856043536.815, "dur": 0.573, + "args": { + "External id": 1446325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 11700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413856043542.983, "dur": 65107.032, + "args": { + "External id": 1446326,"Record function id": 0, "Sequence number": 15348888, "Fwd thread id": 1, "Ev Idx": 11701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413856043544.522, "dur": 65095.942, + "args": { + "External id": 1446327,"Sequence number": 15348888, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11702 + } + }, + { + "ph": "f", "id": 447, "pid": 2338706, "tid": 2379422, "ts": 6413856043544.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413856043574.917, "dur": 40.887, + "args": { + "External id": 1446328,"Record function id": 0, "Ev Idx": 11703 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413856043623.603, "dur": 92.786, + "args": { + "External id": 1446329,"Record function id": 0, "Ev Idx": 11704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 2338706, "tid": 2379422, + "ts": 6413856043725.184, "dur": 64907.061, + "args": { + "External id": 1446330,"Record function id": 0, "Ev Idx": 11705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856043823.792, "dur": 7.316, + "args": { + "External id": 1446331,"Record function id": 0, "Concrete Inputs": ["[218112000]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856043845.288, "dur": 4.925, + "args": { + "External id": 1446332,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 11707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413856043864.431, "dur": 63810.965, + "args": { + "External id": 1446333,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413856043878.706, "dur": 63783.804, + "args": { + "External id": 1446334,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [4096, 1], [4096, 1], [4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], [], [], [27264000, 1]], "Input Dims": [[[4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], [], [], [8, 27264000]], "Ev Idx": 11709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856044010.903, "dur": 20.037, + "args": { + "External id": 1446335,"Record function id": 0, "Concrete Inputs": ["[53306]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413856044051.882, "dur": 63567.377, + "args": { + "External id": 1446336,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], [], []], "Ev Idx": 11711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413856044131.448, "dur": 63486.885, + "args": { + "External id": 1446337,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[53306], [], [], [], [], [], []], "Ev Idx": 11712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856044136.875, "dur": 13.228, + "args": { + "External id": 1446338,"Record function id": 0, "Concrete Inputs": ["[53306]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413856044152.366, "dur": 63461.163, + "args": { + "External id": 1446339,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[53306], [53306], []], "Ev Idx": 11714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856107788.325, "dur": 12.060, + "args": { + "External id": 1446340,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[218112000], [], [], [], [], []], "Ev Idx": 11715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856107791.948, "dur": 7.964, + "args": { + "External id": 1446341,"Record function id": 0, "Concrete Inputs": ["[27264000]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413856107832.718, "dur": 421.387, + "args": { + "External id": 1446342,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[27264000], [218112000], [], [], [], []], "Ev Idx": 11717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413856107861.493, "dur": 386.767, + "args": { + "External id": 1446343,"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": 27264000, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[218112000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11718, "In msg nelems": 218112000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413856107873.611, "dur": 368.541, + "args": { + "External id": 1446344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[218112000]], "Ev Idx": 11719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413856108276.152, "dur": 2.356, + "args": { + "External id": 1446345,"Record function id": 0, "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": 11720, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108344.036, "dur": 6.874, + "args": { + "External id": 1446346,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108363.856, "dur": 33.794, + "args": { + "External id": 1446347,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108408.534, "dur": 1.582, + "args": { + "External id": 1446348,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108416.047, "dur": 11.916, + "args": { + "External id": 1446349,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108433.400, "dur": 0.868, + "args": { + "External id": 1446350,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108438.494, "dur": 11.105, + "args": { + "External id": 1446351,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108454.675, "dur": 1.072, + "args": { + "External id": 1446352,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "2621952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108460.102, "dur": 10.328, + "args": { + "External id": 1446353,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108474.719, "dur": 3.304, + "args": { + "External id": 1446354,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "3146240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108481.577, "dur": 10.526, + "args": { + "External id": 1446355,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108496.583, "dur": 1.131, + "args": { + "External id": 1446356,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108501.754, "dur": 9.603, + "args": { + "External id": 1446357,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108515.857, "dur": 0.633, + "args": { + "External id": 1446358,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "5243904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108522.105, "dur": 10.716, + "args": { + "External id": 1446359,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108537.793, "dur": 0.626, + "args": { + "External id": 1446360,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "12583936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108542.772, "dur": 9.847, + "args": { + "External id": 1446361,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856108557.533, "dur": 0.889, + "args": { + "External id": 1446362,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "19923968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 11737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856108562.274, "dur": 10.515, + "args": { + "External id": 1446363,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413856108666.724, "dur": 267.889, + "args": { + "External id": 1446364,"Record function id": 0, "Sequence number": 15348887, "Fwd thread id": 1, "Ev Idx": 11739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338706, "tid": 2379422, + "ts": 6413856108669.847, "dur": 256.401, + "args": { + "External id": 1446365,"Sequence number": 15348887, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 11740 + } + }, + { + "ph": "f", "id": 448, "pid": 2338706, "tid": 2379422, "ts": 6413856108669.847, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338706, "tid": 2379422, + "ts": 6413856108796.521, "dur": 36.830, + "args": { + "External id": 1446366,"kernel_hash": "cwi477k6wdh6lokdagawsji5sufpvs7jjfv77xwkpv6wyl2co2tv", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/wi/cwi477k6wdh6lokdagawsji5sufpvs7jjfv77xwkpv6wyl2co2tv.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 11741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 2338706, "tid": 2379422, + "ts": 6413856108847.968, "dur": 24.291, + "args": { + "External id": 1446367,"kernel_hash": "cdaibgaofwvuhdtnzghakbdinq55v26czvh7dtqt726q3xahddo3", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/da/cdaibgaofwvuhdtnzghakbdinq55v26czvh7dtqt726q3xahddo3.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096, 4096], [32000, 4096], []], "Ev Idx": 11742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 2338706, "tid": 2379422, + "ts": 6413856108889.998, "dur": 22.093, + "args": { + "External id": 1446368,"kernel_hash": "cozpxeylo6qxtrc76ucyd7ba7bcr4ctg436exqn3bklybds2girm", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/oz/cozpxeylo6qxtrc76ucyd7ba7bcr4ctg436exqn3bklybds2girm.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 11743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856108943.586, "dur": 16.176, + "args": { + "External id": 1446369,"Record function id": 0, "Ev Idx": 11744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338706, "tid": 2379422, + "ts": 6413856108946.465, "dur": 12.543, + "args": { + "External id": 1446370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 11745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856108950.075, "dur": 8.035, + "args": { + "External id": 1446371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 11746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2379422, + "ts": 6413856108951.765, "dur": 6.219, + "args": { + "External id": 1446372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 11747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 2338706, "tid": 2379422, + "ts": 6413856109000.023, "dur": 19761.240, + "args": { + "External id": 1446373,"Record function id": 0, "Ev Idx": 11748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338706, "tid": 2379422, + "ts": 6413856109020.390, "dur": 73.570, + "args": { + "External id": 1446374,"Record function id": 0, "Ev Idx": 11749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338706, "tid": 2379422, + "ts": 6413856109102.129, "dur": 298.369, + "args": { + "External id": 1446375,"Record function id": 0, "Ev Idx": 11750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338706, "tid": 2379422, + "ts": 6413856109406.671, "dur": 19097.695, + "args": { + "External id": 1446376,"Record function id": 0, "Ev Idx": 11751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856109530.030, "dur": 8.418, + "args": { + "External id": 1446377,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2379422, + "ts": 6413856109550.163, "dur": 5.514, + "args": { + "External id": 1446378,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 11753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413856109577.324, "dur": 17146.740, + "args": { + "External id": 1446379,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 11754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 2338706, "tid": 2379422, + "ts": 6413856109616.357, "dur": 17093.057, + "args": { + "External id": 1446380,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [141824512, 1]], "Input Dims": [[], [], [], [8, 141824512]], "Ev Idx": 11755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856110513.017, "dur": 28.018, + "args": { + "External id": 1446381,"Record function id": 0, "Concrete Inputs": ["[277237]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2379422, + "ts": 6413856110786.897, "dur": 15869.254, + "args": { + "External id": 1446382,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], [], []], "Ev Idx": 11757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2379422, + "ts": 6413856110790.761, "dur": 15864.098, + "args": { + "External id": 1446383,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[277237], [], [], [], [], [], []], "Ev Idx": 11758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856110796.782, "dur": 15.284, + "args": { + "External id": 1446384,"Record function id": 0, "Concrete Inputs": ["[277237]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2379422, + "ts": 6413856110814.774, "dur": 15833.322, + "args": { + "External id": 1446385,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[277237], [277237], []], "Ev Idx": 11760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856126879.828, "dur": 14.023, + "args": { + "External id": 1446386,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1134596096], [], [], [], [], []], "Ev Idx": 11761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2379422, + "ts": 6413856126885.147, "dur": 8.271, + "args": { + "External id": 1446387,"Record function id": 0, "Concrete Inputs": ["[141824512]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 2338706, "tid": 2379422, + "ts": 6413856126924.961, "dur": 414.985, + "args": { + "External id": 1446388,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[141824512], [1134596096], [], [], [], []], "Ev Idx": 11763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413856126951.056, "dur": 382.972, + "args": { + "External id": 1446389,"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": 141824512, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[1134596096], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11764, "In msg nelems": 1134596096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 2338706, "tid": 2379422, + "ts": 6413856126961.953, "dur": 365.182, + "args": { + "External id": 1446390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1134596096]], "Ev Idx": 11765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2379422, + "ts": 6413856127361.555, "dur": 2.463, + "args": { + "External id": 1446391,"Record function id": 0, "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": 11766, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127425.995, "dur": 7.277, + "args": { + "External id": 1446392,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127445.852, "dur": 31.705, + "args": { + "External id": 1446393,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4000, 4096], [4000, 4096], []], "Ev Idx": 11768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127488.059, "dur": 1.471, + "args": { + "External id": 1446394,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127496.841, "dur": 11.280, + "args": { + "External id": 1446395,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127513.981, "dur": 0.978, + "args": { + "External id": 1446396,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "16384512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127520.219, "dur": 11.365, + "args": { + "External id": 1446397,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127536.853, "dur": 2.925, + "args": { + "External id": 1446398,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "18481664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127545.339, "dur": 9.796, + "args": { + "External id": 1446399,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127559.574, "dur": 0.785, + "args": { + "External id": 1446400,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "19005952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127622.428, "dur": 12.409, + "args": { + "External id": 1446401,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127641.115, "dur": 0.968, + "args": { + "External id": 1446402,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "19530240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127648.715, "dur": 9.949, + "args": { + "External id": 1446403,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127663.168, "dur": 1.032, + "args": { + "External id": 1446404,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127668.871, "dur": 9.936, + "args": { + "External id": 1446405,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127682.856, "dur": 0.709, + "args": { + "External id": 1446406,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "21627904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127687.048, "dur": 9.615, + "args": { + "External id": 1446407,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127700.619, "dur": 0.745, + "args": { + "External id": 1446408,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "28967936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127705.533, "dur": 9.817, + "args": { + "External id": 1446409,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127721.044, "dur": 0.714, + "args": { + "External id": 1446410,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "36307968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127726.035, "dur": 9.854, + "args": { + "External id": 1446411,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127740.263, "dur": 1.145, + "args": { + "External id": 1446412,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127746.063, "dur": 10.407, + "args": { + "External id": 1446413,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127760.621, "dur": 2.720, + "args": { + "External id": 1446414,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "43648512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127767.390, "dur": 9.658, + "args": { + "External id": 1446415,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127781.336, "dur": 0.825, + "args": { + "External id": 1446416,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "45745664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127786.537, "dur": 9.819, + "args": { + "External id": 1446417,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127800.834, "dur": 0.994, + "args": { + "External id": 1446418,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "46269952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127806.120, "dur": 9.138, + "args": { + "External id": 1446419,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127819.886, "dur": 1.085, + "args": { + "External id": 1446420,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "46794240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127827.433, "dur": 10.505, + "args": { + "External id": 1446421,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127843.055, "dur": 0.892, + "args": { + "External id": 1446422,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127848.497, "dur": 9.860, + "args": { + "External id": 1446423,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127863.187, "dur": 0.973, + "args": { + "External id": 1446424,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "48891904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127868.124, "dur": 9.936, + "args": { + "External id": 1446425,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127882.692, "dur": 1.156, + "args": { + "External id": 1446426,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "56231936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127888.144, "dur": 11.390, + "args": { + "External id": 1446427,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127905.841, "dur": 0.937, + "args": { + "External id": 1446428,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "63571968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127911.514, "dur": 11.786, + "args": { + "External id": 1446429,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127927.804, "dur": 3.123, + "args": { + "External id": 1446430,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127934.655, "dur": 10.855, + "args": { + "External id": 1446431,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127949.915, "dur": 0.819, + "args": { + "External id": 1446432,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "70912512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127955.099, "dur": 12.629, + "args": { + "External id": 1446433,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856127972.371, "dur": 0.844, + "args": { + "External id": 1446434,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73009664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856127977.105, "dur": 28.761, + "args": { + "External id": 1446435,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128013.364, "dur": 1.258, + "args": { + "External id": 1446436,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "73533952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128019.416, "dur": 13.719, + "args": { + "External id": 1446437,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128037.488, "dur": 1.037, + "args": { + "External id": 1446438,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "74058240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128042.515, "dur": 50.104, + "args": { + "External id": 1446439,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128101.829, "dur": 1.568, + "args": { + "External id": 1446440,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128107.966, "dur": 16.279, + "args": { + "External id": 1446441,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128129.256, "dur": 0.961, + "args": { + "External id": 1446442,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "76155904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128134.739, "dur": 11.907, + "args": { + "External id": 1446443,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128151.193, "dur": 0.918, + "args": { + "External id": 1446444,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "83495936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128157.232, "dur": 11.862, + "args": { + "External id": 1446445,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128173.997, "dur": 2.756, + "args": { + "External id": 1446446,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "90835968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128181.590, "dur": 11.186, + "args": { + "External id": 1446447,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128197.363, "dur": 0.737, + "args": { + "External id": 1446448,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128202.917, "dur": 11.864, + "args": { + "External id": 1446449,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128219.346, "dur": 0.880, + "args": { + "External id": 1446450,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "98176512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128225.943, "dur": 10.727, + "args": { + "External id": 1446451,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128241.009, "dur": 0.660, + "args": { + "External id": 1446452,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100273664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128245.577, "dur": 12.299, + "args": { + "External id": 1446453,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128262.904, "dur": 0.773, + "args": { + "External id": 1446454,"Record function id": 0, "Concrete Inputs": ["", "[128, 4096]", "[4096, 1]", "100797952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128268.044, "dur": 11.543, + "args": { + "External id": 1446455,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[128, 4096], [128, 4096], []], "Ev Idx": 11830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128285.409, "dur": 0.663, + "args": { + "External id": 1446456,"Record function id": 0, "Concrete Inputs": ["", "[512, 4096]", "[4096, 1]", "101322240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128289.909, "dur": 12.579, + "args": { + "External id": 1446457,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[512, 4096], [512, 4096], []], "Ev Idx": 11832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128307.117, "dur": 0.856, + "args": { + "External id": 1446458,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128312.037, "dur": 11.865, + "args": { + "External id": 1446459,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128328.553, "dur": 0.823, + "args": { + "External id": 1446460,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "103419904"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128333.611, "dur": 12.415, + "args": { + "External id": 1446461,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128350.737, "dur": 2.796, + "args": { + "External id": 1446462,"Record function id": 0, "Concrete Inputs": ["", "[1792, 4096]", "[4096, 1]", "110759936"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128358.029, "dur": 11.120, + "args": { + "External id": 1446463,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[1792, 4096], [1792, 4096], []], "Ev Idx": 11838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128374.573, "dur": 0.770, + "args": { + "External id": 1446464,"Record function id": 0, "Concrete Inputs": ["", "[512, 14336]", "[14336, 1]", "118099968"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128379.558, "dur": 12.234, + "args": { + "External id": 1446465,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], []], "Input Dims": [[512, 14336], [512, 14336], []], "Ev Idx": 11840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128396.160, "dur": 0.846, + "args": { + "External id": 1446466,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128401.535, "dur": 11.530, + "args": { + "External id": 1446467,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[512], [512], []], "Ev Idx": 11842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2379422, + "ts": 6413856128416.678, "dur": 1.028, + "args": { + "External id": 1446468,"Record function id": 0, "Concrete Inputs": ["", "[4000, 4096]", "[4096, 1]", "125440512"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2379422, + "ts": 6413856128422.360, "dur": 12.476, + "args": { + "External id": 1446469,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4000, 4096], [4000, 4096], []], "Ev Idx": 11844 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "ProfilerStep#32767", "pid": 2338706, "tid": 2338706, + "ts": 6413849637744.887, "dur": 6520968.972, + "args": { + "External id": 1425409,"Record function id": 0, "Ev Idx": 11845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 2338706, "tid": 2338706, + "ts": 6413849637793.467, "dur": 1326.897, + "args": { + "External id": 1425410,"Record function id": 0, "Ev Idx": 11846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 2338706, "tid": 2338706, + "ts": 6413849639205.208, "dur": 2485.055, + "args": { + "External id": 1425411,"Record function id": 0, "Ev Idx": 11847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849640424.605, "dur": 9.314, + "args": { + "External id": 1425412,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338706, "tid": 2338706, + "ts": 6413849640477.859, "dur": 8.643, + "args": { + "External id": 1425413,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 11849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849641019.786, "dur": 2.822, + "args": { + "External id": 1425414,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338706, "tid": 2338706, + "ts": 6413849641034.276, "dur": 3.067, + "args": { + "External id": 1425415,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 11851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849641545.307, "dur": 2.226, + "args": { + "External id": 1425416,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338706, "tid": 2338706, + "ts": 6413849641553.239, "dur": 2.508, + "args": { + "External id": 1425417,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 11853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849642158.729, "dur": 20.445, + "args": { + "External id": 1425418,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 11854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849642171.999, "dur": 2.653, + "args": { + "External id": 1425419,"Record function id": 0, "Concrete Inputs": ["", "[8, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 11855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849642181.116, "dur": 4.474, + "args": { + "External id": 1425420,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 11856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849642183.253, "dur": 1.059, + "args": { + "External id": 1425421,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 11857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849642217.341, "dur": 1580.943, + "args": { + "External id": 1425422,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], [], []], "Ev Idx": 11858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849642225.307, "dur": 1571.961, + "args": { + "External id": 1425423,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 11859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849642237.122, "dur": 11.257, + "args": { + "External id": 1425424,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849642251.116, "dur": 1544.250, + "args": { + "External id": 1425425,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849642262.316, "dur": 0.659, + "args": { + "External id": 1425426,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 11862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849642266.140, "dur": 7.209, + "args": { + "External id": 1425427,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[8, 4096], [8, 4096]], "Ev Idx": 11863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338706, "tid": 2338706, + "ts": 6413849642269.192, "dur": 3.962, + "args": { + "External id": 1425428,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[8, 4096], [], []], "Ev Idx": 11864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849642272.336, "dur": 0.520, + "args": { + "External id": 1425429,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 11865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413849642276.032, "dur": 152.229, + "args": { + "External id": 1425430,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 11866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413849642278.836, "dur": 149.069, + "args": { + "External id": 1425431,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 11867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849642281.556, "dur": 21.455, + "args": { + "External id": 1425432,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 11868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849642286.452, "dur": 15.866, + "args": { + "External id": 1425433,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849642304.108, "dur": 123.302, + "args": { + "External id": 1425434,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849642431.315, "dur": 1360.011, + "args": { + "External id": 1425435,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849643816.900, "dur": 513.125, + "args": { + "External id": 1425436,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 11872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849643819.026, "dur": 510.295, + "args": { + "External id": 1425437,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], []], "Ev Idx": 11873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849643827.554, "dur": 10.712, + "args": { + "External id": 1425438,"Record function id": 0, "Concrete Inputs": ["[8, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849643842.351, "dur": 483.054, + "args": { + "External id": 1425439,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[8, 8192], [8, 8192], []], "Ev Idx": 11875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338706, "tid": 2338706, + "ts": 6413849644363.335, "dur": 61.768, + "args": { + "External id": 1425440,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849644370.346, "dur": 5.873, + "args": { + "External id": 1425441,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338706, "tid": 2338706, + "ts": 6413849644379.553, "dur": 45.004, + "args": { + "External id": 1425442,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 11878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413849644384.678, "dur": 9.561, + "args": { + "External id": 1425443,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 11879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 2338706, "tid": 2338706, + "ts": 6413849644437.970, "dur": 84.028, + "args": { + "External id": 1425444,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338706, "tid": 2338706, + "ts": 6413849644445.972, "dur": 9.884, + "args": { + "External id": 1425445,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 11881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849644453.009, "dur": 2.429, + "args": { + "External id": 1425446,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 11882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849644457.022, "dur": 3.513, + "args": { + "External id": 1425447,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413849644463.259, "dur": 4.652, + "args": { + "External id": 1425448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[8, 4096]], "Ev Idx": 11884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338706, "tid": 2338706, + "ts": 6413849644470.951, "dur": 5.826, + "args": { + "External id": 1425449,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 11885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849644475.825, "dur": 0.711, + "args": { + "External id": 1425450,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 11886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338706, "tid": 2338706, + "ts": 6413849644477.799, "dur": 5.540, + "args": { + "External id": 1425451,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 11887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849644482.140, "dur": 1.055, + "args": { + "External id": 1425452,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 11888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849644485.615, "dur": 6.251, + "args": { + "External id": 1425453,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [8, 1, 1, 4096]], "Ev Idx": 11889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338706, "tid": 2338706, + "ts": 6413849644489.193, "dur": 2.537, + "args": { + "External id": 1425454,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 11890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849644490.555, "dur": 0.991, + "args": { + "External id": 1425455,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 11891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849644493.142, "dur": 28.069, + "args": { + "External id": 1425456,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 4096, 4096, 1], [0, 4096, 4096, 1], []], "Input Dims": [[8, 1, 1, 4096], [8, 1, 1, 4096], []], "Ev Idx": 11892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849644532.700, "dur": 32.738, + "args": { + "External id": 1425457,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 11893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849644534.300, "dur": 30.834, + "args": { + "External id": 1425458,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 11894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849644540.134, "dur": 3.916, + "args": { + "External id": 1425459,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849644545.034, "dur": 19.547, + "args": { + "External id": 1425460,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 11896 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849644696.251, "dur": 171.545, + "args": { + "External id": 1425461,"Record function id": 0, "Ev Idx": 11897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338706, "tid": 2338706, + "ts": 6413849644788.550, "dur": 66.966, + "args": { + "External id": 1425462,"Record function id": 0, "Ev Idx": 11898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849644875.583, "dur": 52.657, + "args": { + "External id": 1425463,"Record function id": 0, "Ev Idx": 11899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849644937.715, "dur": 12572.167, + "args": { + "External id": 1425464,"Record function id": 0, "Ev Idx": 11900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338706, "tid": 2338706, + "ts": 6413849644948.048, "dur": 1686.191, + "args": { + "External id": 1425465,"Record function id": 0, "Ev Idx": 11901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849645149.485, "dur": 12.414, + "args": { + "External id": 1425466,"Record function id": 0, "Concrete Inputs": ["[141824512]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849645186.593, "dur": 153.522, + "args": { + "External id": 1425467,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 11903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645193.086, "dur": 2.651, + "args": { + "External id": 1425468,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645202.226, "dur": 0.573, + "args": { + "External id": 1425469,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645203.825, "dur": 0.363, + "args": { + "External id": 1425470,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "16384512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645205.060, "dur": 3.355, + "args": { + "External id": 1425471,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "18481664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645213.808, "dur": 0.427, + "args": { + "External id": 1425472,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19005952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645215.114, "dur": 0.572, + "args": { + "External id": 1425473,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "19530240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645216.417, "dur": 1.993, + "args": { + "External id": 1425474,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645222.345, "dur": 0.461, + "args": { + "External id": 1425475,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "21627904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645223.865, "dur": 0.369, + "args": { + "External id": 1425476,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "28967936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645229.493, "dur": 0.487, + "args": { + "External id": 1425477,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "36307968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645230.837, "dur": 0.426, + "args": { + "External id": 1425478,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645231.956, "dur": 2.575, + "args": { + "External id": 1425479,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "43648512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645240.379, "dur": 0.438, + "args": { + "External id": 1425480,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "45745664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645241.397, "dur": 0.313, + "args": { + "External id": 1425481,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "46269952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645242.478, "dur": 2.528, + "args": { + "External id": 1425482,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "46794240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645248.164, "dur": 0.416, + "args": { + "External id": 1425483,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645249.461, "dur": 0.376, + "args": { + "External id": 1425484,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "48891904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645254.940, "dur": 0.286, + "args": { + "External id": 1425485,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "56231936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645256.013, "dur": 0.407, + "args": { + "External id": 1425486,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "63571968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645257.170, "dur": 2.655, + "args": { + "External id": 1425487,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645265.188, "dur": 0.450, + "args": { + "External id": 1425488,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "70912512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645266.275, "dur": 0.574, + "args": { + "External id": 1425489,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73009664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645267.773, "dur": 2.830, + "args": { + "External id": 1425490,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73533952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645274.260, "dur": 0.407, + "args": { + "External id": 1425491,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "74058240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645275.492, "dur": 0.304, + "args": { + "External id": 1425492,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645281.168, "dur": 0.295, + "args": { + "External id": 1425493,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "76155904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645282.240, "dur": 0.270, + "args": { + "External id": 1425494,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "83495936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645283.184, "dur": 3.063, + "args": { + "External id": 1425495,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "90835968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645291.351, "dur": 0.400, + "args": { + "External id": 1425496,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645292.480, "dur": 0.276, + "args": { + "External id": 1425497,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "98176512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645293.589, "dur": 2.189, + "args": { + "External id": 1425498,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100273664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645298.711, "dur": 0.466, + "args": { + "External id": 1425499,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100797952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645300.053, "dur": 0.477, + "args": { + "External id": 1425500,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "101322240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645305.104, "dur": 0.422, + "args": { + "External id": 1425501,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645306.313, "dur": 0.418, + "args": { + "External id": 1425502,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "103419904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645307.474, "dur": 3.060, + "args": { + "External id": 1425503,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "110759936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645313.681, "dur": 0.409, + "args": { + "External id": 1425504,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "118099968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645314.957, "dur": 0.557, + "args": { + "External id": 1425505,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645316.328, "dur": 2.207, + "args": { + "External id": 1425506,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "125440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849645372.250, "dur": 165.739, + "args": { + "External id": 1425507,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849645624.809, "dur": 391.723, + "args": { + "External id": 1425508,"Record function id": 0, "Concrete Inputs": ["", "", "141824512", "8", "0", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849645642.451, "dur": 5.520, + "args": { + "External id": 1425509,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849645655.657, "dur": 16.233, + "args": { + "External id": 1425510,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "141824512"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 11946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849645660.860, "dur": 10.526, + "args": { + "External id": 1425511,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "141824512", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[1134596096], [], [], [], []], "Ev Idx": 11947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645667.237, "dur": 1.051, + "args": { + "External id": 1425512,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 11948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849645681.794, "dur": 137.350, + "args": { + "External id": 1425513,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 11949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645683.706, "dur": 0.515, + "args": { + "External id": 1425514,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645685.826, "dur": 0.694, + "args": { + "External id": 1425515,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645690.016, "dur": 2.802, + "args": { + "External id": 1425516,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "16384512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645693.672, "dur": 0.774, + "args": { + "External id": 1425517,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "18481664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645698.003, "dur": 0.446, + "args": { + "External id": 1425518,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19005952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645699.310, "dur": 0.266, + "args": { + "External id": 1425519,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "19530240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645701.042, "dur": 0.305, + "args": { + "External id": 1425520,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645705.118, "dur": 0.527, + "args": { + "External id": 1425521,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "21627904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645706.580, "dur": 0.892, + "args": { + "External id": 1425522,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "28967936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645708.277, "dur": 0.599, + "args": { + "External id": 1425523,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "36307968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645712.554, "dur": 3.406, + "args": { + "External id": 1425524,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645716.986, "dur": 0.443, + "args": { + "External id": 1425525,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "43648512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645720.764, "dur": 1.983, + "args": { + "External id": 1425526,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "45745664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645723.482, "dur": 0.511, + "args": { + "External id": 1425527,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "46269952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645724.746, "dur": 0.465, + "args": { + "External id": 1425528,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "46794240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645730.062, "dur": 0.449, + "args": { + "External id": 1425529,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645731.377, "dur": 0.359, + "args": { + "External id": 1425530,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "48891904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645732.552, "dur": 0.454, + "args": { + "External id": 1425531,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "56231936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645738.884, "dur": 2.601, + "args": { + "External id": 1425532,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "63571968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645742.153, "dur": 0.349, + "args": { + "External id": 1425533,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645745.444, "dur": 2.179, + "args": { + "External id": 1425534,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "70912512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645748.231, "dur": 0.468, + "args": { + "External id": 1425535,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73009664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645749.426, "dur": 0.285, + "args": { + "External id": 1425536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73533952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645754.695, "dur": 0.491, + "args": { + "External id": 1425537,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "74058240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645756.044, "dur": 0.441, + "args": { + "External id": 1425538,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645757.178, "dur": 0.425, + "args": { + "External id": 1425539,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "76155904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645763.176, "dur": 3.126, + "args": { + "External id": 1425540,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "83495936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645766.973, "dur": 0.321, + "args": { + "External id": 1425541,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "90835968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645770.782, "dur": 2.503, + "args": { + "External id": 1425542,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645773.911, "dur": 0.529, + "args": { + "External id": 1425543,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "98176512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645775.311, "dur": 0.456, + "args": { + "External id": 1425544,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100273664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645781.386, "dur": 0.578, + "args": { + "External id": 1425545,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100797952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645782.840, "dur": 0.595, + "args": { + "External id": 1425546,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "101322240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645784.028, "dur": 0.618, + "args": { + "External id": 1425547,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645789.578, "dur": 3.133, + "args": { + "External id": 1425548,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "103419904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645793.627, "dur": 0.371, + "args": { + "External id": 1425549,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "110759936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645796.956, "dur": 2.353, + "args": { + "External id": 1425550,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "118099968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645800.068, "dur": 0.437, + "args": { + "External id": 1425551,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849645801.317, "dur": 0.339, + "args": { + "External id": 1425552,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "125440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 11988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849645846.962, "dur": 125.058, + "args": { + "External id": 1425553,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849646148.456, "dur": 348.019, + "args": { + "External id": 1425554,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[1134596096], [141824512], [], [], []], "Ev Idx": 11990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849646191.184, "dur": 299.287, + "args": { + "External id": 1425555,"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": 1134596096, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[141824512], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11991, "In msg nelems": 141824512 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849646204.395, "dur": 280.160, + "args": { + "External id": 1425556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[141824512]], "Ev Idx": 11992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849646525.262, "dur": 2.539, + "args": { + "External id": 1425557,"Record function id": 0, "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": 11993, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 2338706, "tid": 2338706, + "ts": 6413849646652.370, "dur": 10613.297, + "args": { + "External id": 1425558,"Record function id": 0, "Ev Idx": 11994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646871.310, "dur": 7.950, + "args": { + "External id": 1425559,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 11995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646883.443, "dur": 1.548, + "args": { + "External id": 1425560,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 11996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646887.496, "dur": 1.158, + "args": { + "External id": 1425561,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 11997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646890.931, "dur": 3.639, + "args": { + "External id": 1425562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 11998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646896.148, "dur": 1.268, + "args": { + "External id": 1425563,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 11999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646899.468, "dur": 0.919, + "args": { + "External id": 1425564,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646904.300, "dur": 0.887, + "args": { + "External id": 1425565,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646906.908, "dur": 2.471, + "args": { + "External id": 1425566,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646913.288, "dur": 0.869, + "args": { + "External id": 1425567,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646915.728, "dur": 1.100, + "args": { + "External id": 1425568,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646920.610, "dur": 1.067, + "args": { + "External id": 1425569,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646923.404, "dur": 3.464, + "args": { + "External id": 1425570,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646928.438, "dur": 1.197, + "args": { + "External id": 1425571,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646931.168, "dur": 0.801, + "args": { + "External id": 1425572,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646936.180, "dur": 0.870, + "args": { + "External id": 1425573,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646938.825, "dur": 2.192, + "args": { + "External id": 1425574,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646944.527, "dur": 1.024, + "args": { + "External id": 1425575,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646947.064, "dur": 1.145, + "args": { + "External id": 1425576,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646952.378, "dur": 1.116, + "args": { + "External id": 1425577,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646954.831, "dur": 3.714, + "args": { + "External id": 1425578,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646959.975, "dur": 1.002, + "args": { + "External id": 1425579,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646962.573, "dur": 1.151, + "args": { + "External id": 1425580,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646967.828, "dur": 1.002, + "args": { + "External id": 1425581,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849646970.261, "dur": 2.376, + "args": { + "External id": 1425582,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647023.014, "dur": 3.620, + "args": { + "External id": 1425583,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647028.838, "dur": 0.904, + "args": { + "External id": 1425584,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647033.842, "dur": 1.060, + "args": { + "External id": 1425585,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647036.516, "dur": 3.358, + "args": { + "External id": 1425586,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647041.286, "dur": 1.200, + "args": { + "External id": 1425587,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647044.126, "dur": 1.016, + "args": { + "External id": 1425588,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647048.673, "dur": 0.916, + "args": { + "External id": 1425589,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647051.388, "dur": 2.377, + "args": { + "External id": 1425590,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647101.151, "dur": 3.302, + "args": { + "External id": 1425591,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647109.677, "dur": 1.329, + "args": { + "External id": 1425592,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647115.910, "dur": 1.055, + "args": { + "External id": 1425593,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647119.750, "dur": 4.063, + "args": { + "External id": 1425594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647125.741, "dur": 1.056, + "args": { + "External id": 1425595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647128.557, "dur": 1.013, + "args": { + "External id": 1425596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647134.032, "dur": 0.661, + "args": { + "External id": 1425597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849647136.549, "dur": 2.074, + "args": { + "External id": 1425598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 12034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849647174.699, "dur": 10007.020, + "args": { + "External id": 1425599,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 12035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849647203.122, "dur": 9963.257, + "args": { + "External id": 1425600,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 12036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849647230.757, "dur": 5.964, + "args": { + "External id": 1425601,"Record function id": 0, "Concrete Inputs": ["[4384]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849647242.598, "dur": 9804.097, + "args": { + "External id": 1425602,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], [], []], "Ev Idx": 12038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849647248.124, "dur": 9797.731, + "args": { + "External id": 1425603,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], []], "Ev Idx": 12039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849647255.912, "dur": 8.292, + "args": { + "External id": 1425604,"Record function id": 0, "Concrete Inputs": ["[4384]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849647266.143, "dur": 9774.368, + "args": { + "External id": 1425605,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4384], [4384], []], "Ev Idx": 12041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849657617.630, "dur": 43.660, + "args": { + "External id": 1425606,"Record function id": 0, "Ev Idx": 12042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338706, "tid": 2338706, + "ts": 6413849657664.296, "dur": 264.437, + "args": { + "External id": 1425607,"Record function id": 0, "Ev Idx": 12043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849657719.008, "dur": 199.801, + "args": { + "External id": 1425608,"Sequence number": 15348658, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32000, 4096], [8, 4096]], "Ev Idx": 12044 + } + }, + { + "ph": "s", "id": 224, "pid": 2338706, "tid": 2338706, "ts": 6413849657719.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849657812.731, "dur": 62.615, + "args": { + "External id": 1425609,"kernel_hash": "cwt66mnkcya5wyvezkdac4cj5ntiugvh6bs2jikth6qdzhubcefg", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wt/cwt66mnkcya5wyvezkdac4cj5ntiugvh6bs2jikth6qdzhubcefg.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096], [32000, 4096], [8, 4096, 4096], []], "Ev Idx": 12045 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849658021.780, "dur": 116.755, + "args": { + "External id": 1425610,"Record function id": 0, "Ev Idx": 12046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338706, "tid": 2338706, + "ts": 6413849658154.275, "dur": 8667.524, + "args": { + "External id": 1425611,"Record function id": 0, "Ev Idx": 12047 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338706, "tid": 2338706, + "ts": 6413849658164.020, "dur": 1325.119, + "args": { + "External id": 1425612,"Record function id": 0, "Ev Idx": 12048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849658265.969, "dur": 19.273, + "args": { + "External id": 1425613,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849658311.715, "dur": 64.807, + "args": { + "External id": 1425614,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658325.800, "dur": 4.358, + "args": { + "External id": 1425615,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658333.480, "dur": 0.610, + "args": { + "External id": 1425616,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658335.843, "dur": 2.493, + "args": { + "External id": 1425617,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658342.716, "dur": 0.757, + "args": { + "External id": 1425618,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658345.090, "dur": 0.740, + "args": { + "External id": 1425619,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658352.376, "dur": 0.652, + "args": { + "External id": 1425620,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658354.532, "dur": 0.761, + "args": { + "External id": 1425621,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658356.752, "dur": 2.972, + "args": { + "External id": 1425622,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658365.578, "dur": 0.570, + "args": { + "External id": 1425623,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849658394.152, "dur": 77.908, + "args": { + "External id": 1425624,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849658521.755, "dur": 212.908, + "args": { + "External id": 1425625,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849658541.693, "dur": 10.867, + "args": { + "External id": 1425626,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849658561.337, "dur": 20.239, + "args": { + "External id": 1425627,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849658568.353, "dur": 12.599, + "args": { + "External id": 1425628,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658576.824, "dur": 0.974, + "args": { + "External id": 1425629,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849658595.425, "dur": 45.038, + "args": { + "External id": 1425630,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658598.299, "dur": 0.825, + "args": { + "External id": 1425631,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658603.749, "dur": 0.638, + "args": { + "External id": 1425632,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658607.898, "dur": 1.221, + "args": { + "External id": 1425633,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658612.383, "dur": 0.739, + "args": { + "External id": 1425634,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658614.547, "dur": 5.474, + "args": { + "External id": 1425635,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658622.119, "dur": 0.939, + "args": { + "External id": 1425636,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658627.019, "dur": 0.997, + "args": { + "External id": 1425637,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658632.066, "dur": 0.484, + "args": { + "External id": 1425638,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849658634.099, "dur": 0.480, + "args": { + "External id": 1425639,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849658662.373, "dur": 55.092, + "args": { + "External id": 1425640,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849658821.846, "dur": 518.767, + "args": { + "External id": 1425641,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849658870.424, "dur": 461.315, + "args": { + "External id": 1425642,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12078, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849658885.954, "dur": 433.524, + "args": { + "External id": 1425643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849659377.073, "dur": 4.404, + "args": { + "External id": 1425644,"Record function id": 0, "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": 12080, "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": 2338706, "tid": 2338706, + "ts": 6413849659521.259, "dur": 6931.539, + "args": { + "External id": 1425645,"Record function id": 0, "Ev Idx": 12081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659661.022, "dur": 9.780, + "args": { + "External id": 1425646,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659676.904, "dur": 1.975, + "args": { + "External id": 1425647,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659681.747, "dur": 1.562, + "args": { + "External id": 1425648,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659686.318, "dur": 4.486, + "args": { + "External id": 1425649,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659696.542, "dur": 1.225, + "args": { + "External id": 1425650,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659700.062, "dur": 1.432, + "args": { + "External id": 1425651,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659704.845, "dur": 1.101, + "args": { + "External id": 1425652,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659710.574, "dur": 3.129, + "args": { + "External id": 1425653,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659718.895, "dur": 1.299, + "args": { + "External id": 1425654,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849659722.489, "dur": 1.004, + "args": { + "External id": 1425655,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849659748.218, "dur": 6611.682, + "args": { + "External id": 1425656,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849659773.902, "dur": 6568.143, + "args": { + "External id": 1425657,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849659814.808, "dur": 23.095, + "args": { + "External id": 1425658,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849659846.663, "dur": 6417.939, + "args": { + "External id": 1425659,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849659852.415, "dur": 6410.666, + "args": { + "External id": 1425660,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849659859.632, "dur": 10.906, + "args": { + "External id": 1425661,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849659873.550, "dur": 6380.756, + "args": { + "External id": 1425662,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849666719.632, "dur": 60.094, + "args": { + "External id": 1425663,"Sequence number": 15348659, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12099 + } + }, + { + "ph": "s", "id": 223, "pid": 2338706, "tid": 2338706, "ts": 6413849666719.632, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849666749.551, "dur": 22.347, + "args": { + "External id": 1425664,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849666762.194, "dur": 9.245, + "args": { + "External id": 1425665,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849666887.480, "dur": 153.694, + "args": { + "External id": 1425666,"Record function id": 0, "Ev Idx": 12102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849667044.427, "dur": 2099.652, + "args": { + "External id": 1425667,"Record function id": 0, "Ev Idx": 12103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849667164.605, "dur": 1883.370, + "args": { + "External id": 1425668,"Sequence number": 15348660, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12104 + } + }, + { + "ph": "s", "id": 222, "pid": 2338706, "tid": 2338706, "ts": 6413849667164.605, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849667300.651, "dur": 82.361, + "args": { + "External id": 1425669,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849667405.940, "dur": 143.150, + "args": { + "External id": 1425670,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849667574.426, "dur": 63.397, + "args": { + "External id": 1425671,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849667653.947, "dur": 48.682, + "args": { + "External id": 1425672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849667749.284, "dur": 46.172, + "args": { + "External id": 1425673,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849667835.934, "dur": 33.923, + "args": { + "External id": 1425674,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849667914.250, "dur": 329.592, + "args": { + "External id": 1425675,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849668030.541, "dur": 22.487, + "args": { + "External id": 1425676,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849668039.154, "dur": 12.002, + "args": { + "External id": 1425677,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849668125.640, "dur": 9.348, + "args": { + "External id": 1425678,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849668139.230, "dur": 2.027, + "args": { + "External id": 1425679,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849668145.752, "dur": 5.274, + "args": { + "External id": 1425680,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849668264.065, "dur": 111.972, + "args": { + "External id": 1425681,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849668437.365, "dur": 53.540, + "args": { + "External id": 1425682,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849668504.413, "dur": 75.208, + "args": { + "External id": 1425683,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849668597.128, "dur": 66.507, + "args": { + "External id": 1425684,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849668703.171, "dur": 44.191, + "args": { + "External id": 1425685,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849668760.030, "dur": 66.803, + "args": { + "External id": 1425686,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849668864.157, "dur": 33.541, + "args": { + "External id": 1425687,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12123 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 2338706, "tid": 2338706, + "ts": 6413849669246.952, "dur": 130.283, + "args": { + "External id": 1425688,"Record function id": 0, "Ev Idx": 12124 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849669494.563, "dur": 80.264, + "args": { + "External id": 1425689,"Record function id": 0, "Ev Idx": 12125 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338706, "tid": 2338706, + "ts": 6413849669590.118, "dur": 27184.607, + "args": { + "External id": 1425690,"Record function id": 0, "Ev Idx": 12126 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338706, "tid": 2338706, + "ts": 6413849669608.176, "dur": 1548.355, + "args": { + "External id": 1425691,"Record function id": 0, "Ev Idx": 12127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849669729.259, "dur": 15.088, + "args": { + "External id": 1425692,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849669765.349, "dur": 61.388, + "args": { + "External id": 1425693,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669775.165, "dur": 4.389, + "args": { + "External id": 1425694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669782.219, "dur": 1.035, + "args": { + "External id": 1425695,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669786.807, "dur": 0.786, + "args": { + "External id": 1425696,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669791.680, "dur": 0.941, + "args": { + "External id": 1425697,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669794.360, "dur": 3.075, + "args": { + "External id": 1425698,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669801.912, "dur": 1.106, + "args": { + "External id": 1425699,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669806.931, "dur": 0.539, + "args": { + "External id": 1425700,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669808.999, "dur": 0.429, + "args": { + "External id": 1425701,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849669813.234, "dur": 2.854, + "args": { + "External id": 1425702,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849669844.333, "dur": 91.539, + "args": { + "External id": 1425703,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849670034.146, "dur": 284.989, + "args": { + "External id": 1425704,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849670055.506, "dur": 70.962, + "args": { + "External id": 1425705,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849670140.128, "dur": 16.869, + "args": { + "External id": 1425706,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849670146.137, "dur": 10.191, + "args": { + "External id": 1425707,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670151.809, "dur": 1.345, + "args": { + "External id": 1425708,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849670170.312, "dur": 48.095, + "args": { + "External id": 1425709,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670175.433, "dur": 0.935, + "args": { + "External id": 1425710,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670178.481, "dur": 3.161, + "args": { + "External id": 1425711,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670183.433, "dur": 2.596, + "args": { + "External id": 1425712,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670190.478, "dur": 0.624, + "args": { + "External id": 1425713,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670193.030, "dur": 0.574, + "args": { + "External id": 1425714,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670197.622, "dur": 0.567, + "args": { + "External id": 1425715,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670201.739, "dur": 0.749, + "args": { + "External id": 1425716,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670204.072, "dur": 0.807, + "args": { + "External id": 1425717,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849670210.720, "dur": 0.775, + "args": { + "External id": 1425718,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849670242.753, "dur": 56.715, + "args": { + "External id": 1425719,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849670416.567, "dur": 506.588, + "args": { + "External id": 1425720,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849670459.469, "dur": 454.874, + "args": { + "External id": 1425721,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12157, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849670475.156, "dur": 428.619, + "args": { + "External id": 1425722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849670956.077, "dur": 3.854, + "args": { + "External id": 1425723,"Record function id": 0, "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": 12159, "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": 2338706, "tid": 2338706, + "ts": 6413849671196.324, "dur": 25283.844, + "args": { + "External id": 1425724,"Record function id": 0, "Ev Idx": 12160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671363.784, "dur": 9.719, + "args": { + "External id": 1425725,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671379.601, "dur": 1.736, + "args": { + "External id": 1425726,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671384.352, "dur": 1.844, + "args": { + "External id": 1425727,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671389.256, "dur": 2.419, + "args": { + "External id": 1425728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671394.226, "dur": 1.603, + "args": { + "External id": 1425729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671401.355, "dur": 1.698, + "args": { + "External id": 1425730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671408.254, "dur": 1.555, + "args": { + "External id": 1425731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671412.576, "dur": 5.721, + "args": { + "External id": 1425732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671420.886, "dur": 1.281, + "args": { + "External id": 1425733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849671428.310, "dur": 1.137, + "args": { + "External id": 1425734,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849671455.390, "dur": 24952.014, + "args": { + "External id": 1425735,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849671482.172, "dur": 24912.325, + "args": { + "External id": 1425736,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849671515.670, "dur": 24.364, + "args": { + "External id": 1425737,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849671546.737, "dur": 24789.134, + "args": { + "External id": 1425738,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849671550.347, "dur": 24784.524, + "args": { + "External id": 1425739,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849671558.201, "dur": 9.436, + "args": { + "External id": 1425740,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849671570.647, "dur": 24758.951, + "args": { + "External id": 1425741,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849696694.023, "dur": 46.541, + "args": { + "External id": 1425742,"Sequence number": 15348661, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12178 + } + }, + { + "ph": "s", "id": 221, "pid": 2338706, "tid": 2338706, "ts": 6413849696694.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849696715.517, "dur": 18.188, + "args": { + "External id": 1425743,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849696724.548, "dur": 8.807, + "args": { + "External id": 1425744,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849696835.193, "dur": 100.920, + "args": { + "External id": 1425745,"Record function id": 0, "Ev Idx": 12181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849696938.039, "dur": 1468.812, + "args": { + "External id": 1425746,"Record function id": 0, "Ev Idx": 12182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849697012.914, "dur": 1377.464, + "args": { + "External id": 1425747,"Sequence number": 15348662, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12183 + } + }, + { + "ph": "s", "id": 220, "pid": 2338706, "tid": 2338706, "ts": 6413849697012.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849697159.310, "dur": 66.159, + "args": { + "External id": 1425748,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849697247.434, "dur": 119.384, + "args": { + "External id": 1425749,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849697380.499, "dur": 42.574, + "args": { + "External id": 1425750,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849697430.613, "dur": 32.657, + "args": { + "External id": 1425751,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849697500.177, "dur": 31.850, + "args": { + "External id": 1425752,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849697559.066, "dur": 26.830, + "args": { + "External id": 1425753,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849697609.146, "dur": 169.767, + "args": { + "External id": 1425754,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849697671.346, "dur": 19.171, + "args": { + "External id": 1425755,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849697678.280, "dur": 10.127, + "args": { + "External id": 1425756,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849697695.787, "dur": 8.056, + "args": { + "External id": 1425757,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849697705.400, "dur": 3.889, + "args": { + "External id": 1425758,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849697711.898, "dur": 3.350, + "args": { + "External id": 1425759,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849697792.891, "dur": 59.301, + "args": { + "External id": 1425760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849697893.957, "dur": 38.099, + "args": { + "External id": 1425761,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849697944.167, "dur": 75.128, + "args": { + "External id": 1425762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849698034.427, "dur": 91.570, + "args": { + "External id": 1425763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849698162.162, "dur": 40.161, + "args": { + "External id": 1425764,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849698209.740, "dur": 48.326, + "args": { + "External id": 1425765,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849698284.399, "dur": 25.649, + "args": { + "External id": 1425766,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12202 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 2338706, "tid": 2338706, + "ts": 6413849698484.058, "dur": 94.206, + "args": { + "External id": 1425767,"Record function id": 0, "Ev Idx": 12203 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849698667.303, "dur": 57.685, + "args": { + "External id": 1425768,"Record function id": 0, "Ev Idx": 12204 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338706, "tid": 2338706, + "ts": 6413849698736.093, "dur": 28798.973, + "args": { + "External id": 1425769,"Record function id": 0, "Ev Idx": 12205 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338706, "tid": 2338706, + "ts": 6413849698748.732, "dur": 1045.518, + "args": { + "External id": 1425770,"Record function id": 0, "Ev Idx": 12206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849698843.750, "dur": 10.038, + "args": { + "External id": 1425771,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849698871.445, "dur": 44.383, + "args": { + "External id": 1425772,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698876.987, "dur": 2.330, + "args": { + "External id": 1425773,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698884.130, "dur": 0.515, + "args": { + "External id": 1425774,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698888.101, "dur": 0.520, + "args": { + "External id": 1425775,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698889.737, "dur": 0.600, + "args": { + "External id": 1425776,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698893.042, "dur": 0.537, + "args": { + "External id": 1425777,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698897.342, "dur": 0.762, + "args": { + "External id": 1425778,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698898.950, "dur": 3.297, + "args": { + "External id": 1425779,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698905.964, "dur": 0.697, + "args": { + "External id": 1425780,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849698907.504, "dur": 0.440, + "args": { + "External id": 1425781,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849698929.368, "dur": 88.878, + "args": { + "External id": 1425782,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849699105.274, "dur": 166.233, + "args": { + "External id": 1425783,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849699123.656, "dur": 6.842, + "args": { + "External id": 1425784,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849699137.413, "dur": 12.950, + "args": { + "External id": 1425785,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849699143.028, "dur": 6.847, + "args": { + "External id": 1425786,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699146.746, "dur": 1.011, + "args": { + "External id": 1425787,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849699159.194, "dur": 42.313, + "args": { + "External id": 1425788,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699164.238, "dur": 2.221, + "args": { + "External id": 1425789,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699167.492, "dur": 0.622, + "args": { + "External id": 1425790,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699169.056, "dur": 0.389, + "args": { + "External id": 1425791,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699175.312, "dur": 3.341, + "args": { + "External id": 1425792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699179.450, "dur": 0.417, + "args": { + "External id": 1425793,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699183.581, "dur": 0.272, + "args": { + "External id": 1425794,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699186.942, "dur": 0.336, + "args": { + "External id": 1425795,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699188.218, "dur": 0.323, + "args": { + "External id": 1425796,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849699192.678, "dur": 2.632, + "args": { + "External id": 1425797,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849699216.810, "dur": 44.012, + "args": { + "External id": 1425798,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849699339.470, "dur": 348.601, + "args": { + "External id": 1425799,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849699381.555, "dur": 300.730, + "args": { + "External id": 1425800,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12236, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849699392.988, "dur": 282.790, + "args": { + "External id": 1425801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849699713.991, "dur": 2.558, + "args": { + "External id": 1425802,"Record function id": 0, "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": 12238, "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": 2338706, "tid": 2338706, + "ts": 6413849699818.286, "dur": 27469.023, + "args": { + "External id": 1425803,"Record function id": 0, "Ev Idx": 12239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699933.395, "dur": 6.156, + "args": { + "External id": 1425804,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699943.250, "dur": 1.192, + "args": { + "External id": 1425805,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699946.210, "dur": 3.089, + "args": { + "External id": 1425806,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699951.755, "dur": 1.247, + "args": { + "External id": 1425807,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699954.534, "dur": 1.039, + "args": { + "External id": 1425808,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699957.135, "dur": 1.084, + "args": { + "External id": 1425809,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699962.501, "dur": 1.400, + "args": { + "External id": 1425810,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699966.073, "dur": 2.894, + "args": { + "External id": 1425811,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699970.634, "dur": 0.906, + "args": { + "External id": 1425812,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849699972.845, "dur": 22.570, + "args": { + "External id": 1425813,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849700024.277, "dur": 27203.153, + "args": { + "External id": 1425814,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849700044.693, "dur": 27171.636, + "args": { + "External id": 1425815,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849700104.729, "dur": 20.594, + "args": { + "External id": 1425816,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849700130.997, "dur": 27034.549, + "args": { + "External id": 1425817,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849700133.992, "dur": 27030.464, + "args": { + "External id": 1425818,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849700140.289, "dur": 6.810, + "args": { + "External id": 1425819,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849700149.175, "dur": 27010.243, + "args": { + "External id": 1425820,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849727462.349, "dur": 42.788, + "args": { + "External id": 1425821,"Sequence number": 15348663, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12257 + } + }, + { + "ph": "s", "id": 219, "pid": 2338706, "tid": 2338706, "ts": 6413849727462.349, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849727486.428, "dur": 13.169, + "args": { + "External id": 1425822,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849727492.225, "dur": 7.179, + "args": { + "External id": 1425823,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849727582.446, "dur": 86.934, + "args": { + "External id": 1425824,"Record function id": 0, "Ev Idx": 12260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849727670.936, "dur": 1353.363, + "args": { + "External id": 1425825,"Record function id": 0, "Ev Idx": 12261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849727719.191, "dur": 1286.629, + "args": { + "External id": 1425826,"Sequence number": 15348664, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12262 + } + }, + { + "ph": "s", "id": 218, "pid": 2338706, "tid": 2338706, "ts": 6413849727719.191, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849727804.799, "dur": 58.993, + "args": { + "External id": 1425827,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849727879.457, "dur": 136.539, + "args": { + "External id": 1425828,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849728036.696, "dur": 99.799, + "args": { + "External id": 1425829,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849728156.610, "dur": 42.170, + "args": { + "External id": 1425830,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849728231.856, "dur": 34.689, + "args": { + "External id": 1425831,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849728290.348, "dur": 23.384, + "args": { + "External id": 1425832,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849728339.454, "dur": 157.713, + "args": { + "External id": 1425833,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849728400.345, "dur": 15.240, + "args": { + "External id": 1425834,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849728409.274, "dur": 5.495, + "args": { + "External id": 1425835,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849728418.509, "dur": 5.676, + "args": { + "External id": 1425836,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849728425.422, "dur": 1.174, + "args": { + "External id": 1425837,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849728429.506, "dur": 5.659, + "args": { + "External id": 1425838,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849728509.679, "dur": 59.531, + "args": { + "External id": 1425839,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849728607.642, "dur": 35.376, + "args": { + "External id": 1425840,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849728653.960, "dur": 48.919, + "args": { + "External id": 1425841,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849728712.214, "dur": 39.453, + "args": { + "External id": 1425842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849728776.035, "dur": 32.261, + "args": { + "External id": 1425843,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849728816.516, "dur": 39.667, + "args": { + "External id": 1425844,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849728881.198, "dur": 20.559, + "args": { + "External id": 1425845,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 2338706, "tid": 2338706, + "ts": 6413849729143.233, "dur": 97.964, + "args": { + "External id": 1425846,"Record function id": 0, "Ev Idx": 12282 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849729328.647, "dur": 57.042, + "args": { + "External id": 1425847,"Record function id": 0, "Ev Idx": 12283 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338706, "tid": 2338706, + "ts": 6413849729396.442, "dur": 29552.301, + "args": { + "External id": 1425848,"Record function id": 0, "Ev Idx": 12284 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338706, "tid": 2338706, + "ts": 6413849729408.177, "dur": 1130.016, + "args": { + "External id": 1425849,"Record function id": 0, "Ev Idx": 12285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849729502.909, "dur": 11.856, + "args": { + "External id": 1425850,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849729530.330, "dur": 48.518, + "args": { + "External id": 1425851,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729536.540, "dur": 2.674, + "args": { + "External id": 1425852,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729545.709, "dur": 0.524, + "args": { + "External id": 1425853,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729547.224, "dur": 0.387, + "args": { + "External id": 1425854,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729554.118, "dur": 0.514, + "args": { + "External id": 1425855,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729558.788, "dur": 0.616, + "args": { + "External id": 1425856,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729560.318, "dur": 0.513, + "args": { + "External id": 1425857,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729563.595, "dur": 4.640, + "args": { + "External id": 1425858,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729569.191, "dur": 0.621, + "args": { + "External id": 1425859,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729570.576, "dur": 0.616, + "args": { + "External id": 1425860,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849729594.819, "dur": 68.312, + "args": { + "External id": 1425861,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849729701.723, "dur": 160.132, + "args": { + "External id": 1425862,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849729717.479, "dur": 4.759, + "args": { + "External id": 1425863,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849729727.806, "dur": 10.785, + "args": { + "External id": 1425864,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849729732.697, "dur": 5.392, + "args": { + "External id": 1425865,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729736.150, "dur": 0.649, + "args": { + "External id": 1425866,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849729749.144, "dur": 35.669, + "args": { + "External id": 1425867,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729750.829, "dur": 2.830, + "args": { + "External id": 1425868,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729754.392, "dur": 0.307, + "args": { + "External id": 1425869,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729758.223, "dur": 0.291, + "args": { + "External id": 1425870,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729761.071, "dur": 2.843, + "args": { + "External id": 1425871,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729767.033, "dur": 0.273, + "args": { + "External id": 1425872,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729768.023, "dur": 0.266, + "args": { + "External id": 1425873,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729771.393, "dur": 0.330, + "args": { + "External id": 1425874,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729775.593, "dur": 0.346, + "args": { + "External id": 1425875,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849729776.832, "dur": 1.786, + "args": { + "External id": 1425876,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849729811.159, "dur": 39.961, + "args": { + "External id": 1425877,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849729926.705, "dur": 487.195, + "args": { + "External id": 1425878,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849729963.708, "dur": 443.959, + "args": { + "External id": 1425879,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12315, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849730004.602, "dur": 395.612, + "args": { + "External id": 1425880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849730445.333, "dur": 2.825, + "args": { + "External id": 1425881,"Record function id": 0, "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": 12317, "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": 2338706, "tid": 2338706, + "ts": 6413849730564.172, "dur": 28105.401, + "args": { + "External id": 1425882,"Record function id": 0, "Ev Idx": 12318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730682.401, "dur": 7.925, + "args": { + "External id": 1425883,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730694.314, "dur": 1.647, + "args": { + "External id": 1425884,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730697.949, "dur": 4.145, + "args": { + "External id": 1425885,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730704.105, "dur": 0.977, + "args": { + "External id": 1425886,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730706.845, "dur": 1.219, + "args": { + "External id": 1425887,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730711.542, "dur": 1.083, + "args": { + "External id": 1425888,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730714.230, "dur": 1.191, + "args": { + "External id": 1425889,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730717.385, "dur": 2.620, + "args": { + "External id": 1425890,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730721.625, "dur": 0.774, + "args": { + "External id": 1425891,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849730726.217, "dur": 1.453, + "args": { + "External id": 1425892,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849730749.405, "dur": 27854.761, + "args": { + "External id": 1425893,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849730767.661, "dur": 27825.392, + "args": { + "External id": 1425894,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849730788.871, "dur": 22.232, + "args": { + "External id": 1425895,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849730815.026, "dur": 27731.077, + "args": { + "External id": 1425896,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849730818.006, "dur": 27726.808, + "args": { + "External id": 1425897,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849730826.503, "dur": 8.590, + "args": { + "External id": 1425898,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849730837.115, "dur": 27703.413, + "args": { + "External id": 1425899,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849758863.112, "dur": 48.798, + "args": { + "External id": 1425900,"Sequence number": 15348665, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12336 + } + }, + { + "ph": "s", "id": 217, "pid": 2338706, "tid": 2338706, "ts": 6413849758863.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849758893.177, "dur": 11.922, + "args": { + "External id": 1425901,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849758897.884, "dur": 6.868, + "args": { + "External id": 1425902,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849759018.265, "dur": 122.477, + "args": { + "External id": 1425903,"Record function id": 0, "Ev Idx": 12339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849759147.534, "dur": 1471.835, + "args": { + "External id": 1425904,"Record function id": 0, "Ev Idx": 12340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849759202.032, "dur": 1398.971, + "args": { + "External id": 1425905,"Sequence number": 15348666, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12341 + } + }, + { + "ph": "s", "id": 216, "pid": 2338706, "tid": 2338706, "ts": 6413849759202.032, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849759295.951, "dur": 62.316, + "args": { + "External id": 1425906,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849759376.701, "dur": 119.699, + "args": { + "External id": 1425907,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849759516.289, "dur": 44.788, + "args": { + "External id": 1425908,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849759568.684, "dur": 33.773, + "args": { + "External id": 1425909,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849759637.788, "dur": 31.298, + "args": { + "External id": 1425910,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849759693.942, "dur": 22.204, + "args": { + "External id": 1425911,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849759743.451, "dur": 163.833, + "args": { + "External id": 1425912,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849759806.794, "dur": 14.772, + "args": { + "External id": 1425913,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849759813.578, "dur": 6.750, + "args": { + "External id": 1425914,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849759825.610, "dur": 4.704, + "args": { + "External id": 1425915,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849759832.072, "dur": 1.112, + "args": { + "External id": 1425916,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849759837.493, "dur": 6.361, + "args": { + "External id": 1425917,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849759922.385, "dur": 78.454, + "args": { + "External id": 1425918,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849760091.493, "dur": 42.856, + "args": { + "External id": 1425919,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849760152.617, "dur": 59.273, + "args": { + "External id": 1425920,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849760297.399, "dur": 44.426, + "args": { + "External id": 1425921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849760384.015, "dur": 36.466, + "args": { + "External id": 1425922,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849760427.729, "dur": 42.362, + "args": { + "External id": 1425923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849760490.688, "dur": 24.901, + "args": { + "External id": 1425924,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12360 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 2338706, "tid": 2338706, + "ts": 6413849760695.793, "dur": 92.582, + "args": { + "External id": 1425925,"Record function id": 0, "Ev Idx": 12361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849760876.583, "dur": 53.385, + "args": { + "External id": 1425926,"Record function id": 0, "Ev Idx": 12362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338706, "tid": 2338706, + "ts": 6413849760940.310, "dur": 28184.285, + "args": { + "External id": 1425927,"Record function id": 0, "Ev Idx": 12363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338706, "tid": 2338706, + "ts": 6413849760953.904, "dur": 1252.115, + "args": { + "External id": 1425928,"Record function id": 0, "Ev Idx": 12364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849761120.088, "dur": 12.460, + "args": { + "External id": 1425929,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849761150.176, "dur": 46.929, + "args": { + "External id": 1425930,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761158.650, "dur": 2.432, + "args": { + "External id": 1425931,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761165.559, "dur": 0.540, + "args": { + "External id": 1425932,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761167.040, "dur": 0.592, + "args": { + "External id": 1425933,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761170.731, "dur": 0.671, + "args": { + "External id": 1425934,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761174.663, "dur": 0.341, + "args": { + "External id": 1425935,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761177.705, "dur": 0.607, + "args": { + "External id": 1425936,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761178.947, "dur": 5.181, + "args": { + "External id": 1425937,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761184.900, "dur": 0.649, + "args": { + "External id": 1425938,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761188.836, "dur": 0.492, + "args": { + "External id": 1425939,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849761209.789, "dur": 67.213, + "args": { + "External id": 1425940,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849761317.473, "dur": 149.810, + "args": { + "External id": 1425941,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849761333.220, "dur": 5.088, + "args": { + "External id": 1425942,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849761344.202, "dur": 13.814, + "args": { + "External id": 1425943,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849761349.380, "dur": 8.167, + "args": { + "External id": 1425944,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761355.472, "dur": 0.596, + "args": { + "External id": 1425945,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849761364.926, "dur": 35.822, + "args": { + "External id": 1425946,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761366.616, "dur": 3.179, + "args": { + "External id": 1425947,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761373.345, "dur": 0.511, + "args": { + "External id": 1425948,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761374.574, "dur": 0.439, + "args": { + "External id": 1425949,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761380.584, "dur": 3.121, + "args": { + "External id": 1425950,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761384.270, "dur": 0.536, + "args": { + "External id": 1425951,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761385.487, "dur": 0.438, + "args": { + "External id": 1425952,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761390.625, "dur": 0.341, + "args": { + "External id": 1425953,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761391.694, "dur": 0.615, + "args": { + "External id": 1425954,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849761393.104, "dur": 2.545, + "args": { + "External id": 1425955,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849761417.915, "dur": 38.770, + "args": { + "External id": 1425956,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849761534.204, "dur": 511.779, + "args": { + "External id": 1425957,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849761573.407, "dur": 465.519, + "args": { + "External id": 1425958,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12394, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849761585.036, "dur": 447.129, + "args": { + "External id": 1425959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849762110.866, "dur": 3.664, + "args": { + "External id": 1425960,"Record function id": 0, "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": 12396, "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": 2338706, "tid": 2338706, + "ts": 6413849762231.068, "dur": 26580.372, + "args": { + "External id": 1425961,"Record function id": 0, "Ev Idx": 12397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762353.796, "dur": 7.941, + "args": { + "External id": 1425962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762365.565, "dur": 1.672, + "args": { + "External id": 1425963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762369.503, "dur": 3.710, + "args": { + "External id": 1425964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762375.657, "dur": 0.800, + "args": { + "External id": 1425965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762378.140, "dur": 1.098, + "args": { + "External id": 1425966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762380.664, "dur": 0.973, + "args": { + "External id": 1425967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762385.907, "dur": 1.144, + "args": { + "External id": 1425968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762391.167, "dur": 3.053, + "args": { + "External id": 1425969,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762395.768, "dur": 1.152, + "args": { + "External id": 1425970,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849762398.470, "dur": 1.010, + "args": { + "External id": 1425971,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849762421.522, "dur": 26329.324, + "args": { + "External id": 1425972,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849762441.699, "dur": 26297.981, + "args": { + "External id": 1425973,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849762463.244, "dur": 19.239, + "args": { + "External id": 1425974,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849762486.844, "dur": 26207.278, + "args": { + "External id": 1425975,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849762489.702, "dur": 26202.828, + "args": { + "External id": 1425976,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849762495.697, "dur": 7.309, + "args": { + "External id": 1425977,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849762505.047, "dur": 26183.506, + "args": { + "External id": 1425978,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849789008.316, "dur": 77.192, + "args": { + "External id": 1425979,"Sequence number": 15348667, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12415 + } + }, + { + "ph": "s", "id": 215, "pid": 2338706, "tid": 2338706, "ts": 6413849789008.316, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849789031.622, "dur": 15.709, + "args": { + "External id": 1425980,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849789039.587, "dur": 7.108, + "args": { + "External id": 1425981,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849789178.509, "dur": 89.425, + "args": { + "External id": 1425982,"Record function id": 0, "Ev Idx": 12418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849789269.267, "dur": 1396.874, + "args": { + "External id": 1425983,"Record function id": 0, "Ev Idx": 12419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849789318.727, "dur": 1329.774, + "args": { + "External id": 1425984,"Sequence number": 15348668, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12420 + } + }, + { + "ph": "s", "id": 214, "pid": 2338706, "tid": 2338706, "ts": 6413849789318.727, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849789403.581, "dur": 61.259, + "args": { + "External id": 1425985,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849789481.769, "dur": 119.840, + "args": { + "External id": 1425986,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849789617.122, "dur": 43.433, + "args": { + "External id": 1425987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849789670.053, "dur": 33.862, + "args": { + "External id": 1425988,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849789735.193, "dur": 35.231, + "args": { + "External id": 1425989,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849789797.490, "dur": 23.798, + "args": { + "External id": 1425990,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849789846.535, "dur": 178.562, + "args": { + "External id": 1425991,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849789900.968, "dur": 14.367, + "args": { + "External id": 1425992,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849789907.574, "dur": 6.887, + "args": { + "External id": 1425993,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849789919.589, "dur": 5.628, + "args": { + "External id": 1425994,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849789929.054, "dur": 1.267, + "args": { + "External id": 1425995,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849789933.142, "dur": 6.200, + "args": { + "External id": 1425996,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849790043.351, "dur": 133.579, + "args": { + "External id": 1425997,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849790241.645, "dur": 42.079, + "args": { + "External id": 1425998,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849790296.509, "dur": 57.727, + "args": { + "External id": 1425999,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849790363.509, "dur": 42.313, + "args": { + "External id": 1426000,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849790433.414, "dur": 33.600, + "args": { + "External id": 1426001,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849790476.529, "dur": 43.658, + "args": { + "External id": 1426002,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849790540.454, "dur": 23.280, + "args": { + "External id": 1426003,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12439 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 2338706, "tid": 2338706, + "ts": 6413849790742.536, "dur": 95.096, + "args": { + "External id": 1426004,"Record function id": 0, "Ev Idx": 12440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849790928.490, "dur": 79.808, + "args": { + "External id": 1426005,"Record function id": 0, "Ev Idx": 12441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338706, "tid": 2338706, + "ts": 6413849791021.265, "dur": 31273.078, + "args": { + "External id": 1426006,"Record function id": 0, "Ev Idx": 12442 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338706, "tid": 2338706, + "ts": 6413849791035.386, "dur": 1197.837, + "args": { + "External id": 1426007,"Record function id": 0, "Ev Idx": 12443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849791179.784, "dur": 12.693, + "args": { + "External id": 1426008,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849791209.441, "dur": 50.232, + "args": { + "External id": 1426009,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791219.136, "dur": 2.744, + "args": { + "External id": 1426010,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791226.010, "dur": 0.514, + "args": { + "External id": 1426011,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791229.595, "dur": 0.667, + "args": { + "External id": 1426012,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791231.052, "dur": 0.425, + "args": { + "External id": 1426013,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791234.163, "dur": 0.390, + "args": { + "External id": 1426014,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791238.727, "dur": 0.414, + "args": { + "External id": 1426015,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791240.044, "dur": 4.821, + "args": { + "External id": 1426016,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791245.832, "dur": 0.574, + "args": { + "External id": 1426017,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791250.767, "dur": 0.480, + "args": { + "External id": 1426018,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849791274.083, "dur": 66.782, + "args": { + "External id": 1426019,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849791380.499, "dur": 155.000, + "args": { + "External id": 1426020,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849791399.437, "dur": 4.366, + "args": { + "External id": 1426021,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849791410.069, "dur": 13.748, + "args": { + "External id": 1426022,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849791417.541, "dur": 5.814, + "args": { + "External id": 1426023,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791421.141, "dur": 0.636, + "args": { + "External id": 1426024,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849791431.150, "dur": 40.050, + "args": { + "External id": 1426025,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791435.461, "dur": 2.167, + "args": { + "External id": 1426026,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791438.701, "dur": 0.529, + "args": { + "External id": 1426027,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791439.996, "dur": 0.600, + "args": { + "External id": 1426028,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791446.109, "dur": 2.713, + "args": { + "External id": 1426029,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791449.916, "dur": 0.439, + "args": { + "External id": 1426030,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791451.338, "dur": 0.404, + "args": { + "External id": 1426031,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791456.867, "dur": 0.569, + "args": { + "External id": 1426032,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791458.270, "dur": 0.365, + "args": { + "External id": 1426033,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849791461.879, "dur": 2.393, + "args": { + "External id": 1426034,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849791485.362, "dur": 38.649, + "args": { + "External id": 1426035,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849791600.030, "dur": 513.355, + "args": { + "External id": 1426036,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849791639.039, "dur": 467.398, + "args": { + "External id": 1426037,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12473, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849791650.710, "dur": 446.466, + "args": { + "External id": 1426038,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849792142.615, "dur": 3.367, + "args": { + "External id": 1426039,"Record function id": 0, "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": 12475, "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": 2338706, "tid": 2338706, + "ts": 6413849792257.682, "dur": 29699.835, + "args": { + "External id": 1426040,"Record function id": 0, "Ev Idx": 12476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792379.356, "dur": 7.194, + "args": { + "External id": 1426041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792391.049, "dur": 1.243, + "args": { + "External id": 1426042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792394.463, "dur": 4.094, + "args": { + "External id": 1426043,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792400.992, "dur": 1.385, + "args": { + "External id": 1426044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792404.048, "dur": 1.146, + "args": { + "External id": 1426045,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792408.946, "dur": 1.331, + "args": { + "External id": 1426046,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792414.257, "dur": 1.245, + "args": { + "External id": 1426047,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792417.341, "dur": 3.349, + "args": { + "External id": 1426048,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792422.425, "dur": 0.823, + "args": { + "External id": 1426049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849792426.924, "dur": 0.923, + "args": { + "External id": 1426050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849792447.356, "dur": 29443.543, + "args": { + "External id": 1426051,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849792475.541, "dur": 29403.544, + "args": { + "External id": 1426052,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849792493.545, "dur": 18.941, + "args": { + "External id": 1426053,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849792516.732, "dur": 29315.360, + "args": { + "External id": 1426054,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849792520.079, "dur": 29310.570, + "args": { + "External id": 1426055,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849792526.429, "dur": 7.047, + "args": { + "External id": 1426056,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849792535.396, "dur": 29290.596, + "args": { + "External id": 1426057,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849822210.603, "dur": 46.841, + "args": { + "External id": 1426058,"Sequence number": 15348669, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12494 + } + }, + { + "ph": "s", "id": 213, "pid": 2338706, "tid": 2338706, "ts": 6413849822210.603, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849822232.538, "dur": 17.993, + "args": { + "External id": 1426059,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849822241.527, "dur": 7.848, + "args": { + "External id": 1426060,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849822350.645, "dur": 87.285, + "args": { + "External id": 1426061,"Record function id": 0, "Ev Idx": 12497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849822439.525, "dur": 1325.027, + "args": { + "External id": 1426062,"Record function id": 0, "Ev Idx": 12498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849822483.735, "dur": 1264.874, + "args": { + "External id": 1426063,"Sequence number": 15348670, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12499 + } + }, + { + "ph": "s", "id": 212, "pid": 2338706, "tid": 2338706, "ts": 6413849822483.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849822566.510, "dur": 51.836, + "args": { + "External id": 1426064,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849822633.739, "dur": 122.484, + "args": { + "External id": 1426065,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849822771.498, "dur": 42.563, + "args": { + "External id": 1426066,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849822825.603, "dur": 36.417, + "args": { + "External id": 1426067,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849822893.052, "dur": 31.466, + "args": { + "External id": 1426068,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849822947.508, "dur": 22.835, + "args": { + "External id": 1426069,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849823022.586, "dur": 214.991, + "args": { + "External id": 1426070,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849823126.944, "dur": 16.382, + "args": { + "External id": 1426071,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849823133.775, "dur": 8.285, + "args": { + "External id": 1426072,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849823149.730, "dur": 7.233, + "args": { + "External id": 1426073,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849823158.297, "dur": 2.432, + "args": { + "External id": 1426074,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849823163.451, "dur": 5.877, + "args": { + "External id": 1426075,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849823251.807, "dur": 68.797, + "args": { + "External id": 1426076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849823366.900, "dur": 38.648, + "args": { + "External id": 1426077,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849823416.503, "dur": 51.726, + "args": { + "External id": 1426078,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849823477.725, "dur": 41.875, + "args": { + "External id": 1426079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849823545.111, "dur": 33.038, + "args": { + "External id": 1426080,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849823586.530, "dur": 41.820, + "args": { + "External id": 1426081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849823649.082, "dur": 23.451, + "args": { + "External id": 1426082,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12518 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 2338706, "tid": 2338706, + "ts": 6413849823839.230, "dur": 88.893, + "args": { + "External id": 1426083,"Record function id": 0, "Ev Idx": 12519 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849824040.740, "dur": 101.226, + "args": { + "External id": 1426084,"Record function id": 0, "Ev Idx": 12520 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338706, "tid": 2338706, + "ts": 6413849824154.723, "dur": 32076.805, + "args": { + "External id": 1426085,"Record function id": 0, "Ev Idx": 12521 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338706, "tid": 2338706, + "ts": 6413849824169.459, "dur": 1123.144, + "args": { + "External id": 1426086,"Record function id": 0, "Ev Idx": 12522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849824267.422, "dur": 11.732, + "args": { + "External id": 1426087,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849824296.088, "dur": 46.881, + "args": { + "External id": 1426088,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824301.874, "dur": 2.914, + "args": { + "External id": 1426089,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824308.797, "dur": 0.471, + "args": { + "External id": 1426090,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824313.100, "dur": 0.521, + "args": { + "External id": 1426091,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824314.643, "dur": 0.395, + "args": { + "External id": 1426092,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824319.541, "dur": 0.457, + "args": { + "External id": 1426093,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824320.976, "dur": 0.556, + "args": { + "External id": 1426094,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824322.474, "dur": 4.206, + "args": { + "External id": 1426095,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824329.991, "dur": 0.517, + "args": { + "External id": 1426096,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824331.673, "dur": 0.275, + "args": { + "External id": 1426097,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849824358.235, "dur": 65.353, + "args": { + "External id": 1426098,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849824465.802, "dur": 153.032, + "args": { + "External id": 1426099,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849824480.756, "dur": 5.152, + "args": { + "External id": 1426100,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849824491.814, "dur": 14.514, + "args": { + "External id": 1426101,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849824500.191, "dur": 5.658, + "args": { + "External id": 1426102,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824503.655, "dur": 0.788, + "args": { + "External id": 1426103,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849824514.061, "dur": 39.627, + "args": { + "External id": 1426104,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824518.236, "dur": 2.031, + "args": { + "External id": 1426105,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824521.242, "dur": 0.543, + "args": { + "External id": 1426106,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824525.490, "dur": 0.440, + "args": { + "External id": 1426107,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824529.498, "dur": 2.500, + "args": { + "External id": 1426108,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824532.856, "dur": 0.345, + "args": { + "External id": 1426109,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824536.783, "dur": 0.577, + "args": { + "External id": 1426110,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824539.939, "dur": 0.401, + "args": { + "External id": 1426111,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824541.058, "dur": 0.367, + "args": { + "External id": 1426112,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849824545.047, "dur": 2.067, + "args": { + "External id": 1426113,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849824566.581, "dur": 41.368, + "args": { + "External id": 1426114,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849824680.524, "dur": 489.660, + "args": { + "External id": 1426115,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849824717.527, "dur": 445.658, + "args": { + "External id": 1426116,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12552, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849824728.911, "dur": 426.945, + "args": { + "External id": 1426117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849825201.930, "dur": 3.003, + "args": { + "External id": 1426118,"Record function id": 0, "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": 12554, "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": 2338706, "tid": 2338706, + "ts": 6413849825317.694, "dur": 30578.028, + "args": { + "External id": 1426119,"Record function id": 0, "Ev Idx": 12555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825437.649, "dur": 7.258, + "args": { + "External id": 1426120,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825448.605, "dur": 1.246, + "args": { + "External id": 1426121,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825451.990, "dur": 4.051, + "args": { + "External id": 1426122,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825458.141, "dur": 1.258, + "args": { + "External id": 1426123,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825461.101, "dur": 0.984, + "args": { + "External id": 1426124,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825463.451, "dur": 1.357, + "args": { + "External id": 1426125,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825468.660, "dur": 1.131, + "args": { + "External id": 1426126,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825471.567, "dur": 3.553, + "args": { + "External id": 1426127,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825476.837, "dur": 1.122, + "args": { + "External id": 1426128,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849825479.770, "dur": 1.289, + "args": { + "External id": 1426129,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849825505.995, "dur": 30323.049, + "args": { + "External id": 1426130,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849825525.091, "dur": 30292.070, + "args": { + "External id": 1426131,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849825553.452, "dur": 23.973, + "args": { + "External id": 1426132,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849825581.577, "dur": 30187.563, + "args": { + "External id": 1426133,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849825584.559, "dur": 30183.370, + "args": { + "External id": 1426134,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849825593.470, "dur": 6.155, + "args": { + "External id": 1426135,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849825601.470, "dur": 30161.964, + "args": { + "External id": 1426136,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849856147.716, "dur": 43.841, + "args": { + "External id": 1426137,"Sequence number": 15348671, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12573 + } + }, + { + "ph": "s", "id": 211, "pid": 2338706, "tid": 2338706, "ts": 6413849856147.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849856169.203, "dur": 15.443, + "args": { + "External id": 1426138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849856175.452, "dur": 8.686, + "args": { + "External id": 1426139,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849856287.383, "dur": 89.264, + "args": { + "External id": 1426140,"Record function id": 0, "Ev Idx": 12576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849856378.292, "dur": 1367.401, + "args": { + "External id": 1426141,"Record function id": 0, "Ev Idx": 12577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849856429.085, "dur": 1299.574, + "args": { + "External id": 1426142,"Sequence number": 15348672, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12578 + } + }, + { + "ph": "s", "id": 210, "pid": 2338706, "tid": 2338706, "ts": 6413849856429.085, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849856522.349, "dur": 65.987, + "args": { + "External id": 1426143,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849856605.191, "dur": 119.296, + "args": { + "External id": 1426144,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849856740.906, "dur": 44.285, + "args": { + "External id": 1426145,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849856794.551, "dur": 34.600, + "args": { + "External id": 1426146,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849856864.051, "dur": 32.307, + "args": { + "External id": 1426147,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849856918.192, "dur": 23.010, + "args": { + "External id": 1426148,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849856965.653, "dur": 226.078, + "args": { + "External id": 1426149,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849857046.153, "dur": 57.486, + "args": { + "External id": 1426150,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849857091.937, "dur": 9.352, + "args": { + "External id": 1426151,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849857106.798, "dur": 4.641, + "args": { + "External id": 1426152,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849857112.693, "dur": 1.253, + "args": { + "External id": 1426153,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849857116.627, "dur": 7.663, + "args": { + "External id": 1426154,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849857208.427, "dur": 68.205, + "args": { + "External id": 1426155,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849857320.273, "dur": 38.296, + "args": { + "External id": 1426156,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849857371.402, "dur": 54.409, + "args": { + "External id": 1426157,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849857434.476, "dur": 41.903, + "args": { + "External id": 1426158,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849857505.917, "dur": 39.258, + "args": { + "External id": 1426159,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849857554.011, "dur": 44.016, + "args": { + "External id": 1426160,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849857622.660, "dur": 25.292, + "args": { + "External id": 1426161,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 2338706, "tid": 2338706, + "ts": 6413849857819.706, "dur": 92.198, + "args": { + "External id": 1426162,"Record function id": 0, "Ev Idx": 12598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849858021.748, "dur": 105.791, + "args": { + "External id": 1426163,"Record function id": 0, "Ev Idx": 12599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338706, "tid": 2338706, + "ts": 6413849858140.854, "dur": 35310.333, + "args": { + "External id": 1426164,"Record function id": 0, "Ev Idx": 12600 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338706, "tid": 2338706, + "ts": 6413849858153.917, "dur": 1121.670, + "args": { + "External id": 1426165,"Record function id": 0, "Ev Idx": 12601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849858253.241, "dur": 11.705, + "args": { + "External id": 1426166,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849858283.705, "dur": 43.506, + "args": { + "External id": 1426167,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858289.577, "dur": 2.456, + "args": { + "External id": 1426168,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858298.512, "dur": 0.432, + "args": { + "External id": 1426169,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858299.767, "dur": 0.361, + "args": { + "External id": 1426170,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858300.888, "dur": 0.605, + "args": { + "External id": 1426171,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858305.957, "dur": 0.460, + "args": { + "External id": 1426172,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858307.101, "dur": 0.467, + "args": { + "External id": 1426173,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858310.102, "dur": 4.490, + "args": { + "External id": 1426174,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858315.529, "dur": 0.524, + "args": { + "External id": 1426175,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858316.796, "dur": 0.399, + "args": { + "External id": 1426176,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849858343.981, "dur": 70.389, + "args": { + "External id": 1426177,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849858454.777, "dur": 147.484, + "args": { + "External id": 1426178,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849858470.584, "dur": 4.265, + "args": { + "External id": 1426179,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849858481.198, "dur": 13.729, + "args": { + "External id": 1426180,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849858488.650, "dur": 5.777, + "args": { + "External id": 1426181,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858492.262, "dur": 0.681, + "args": { + "External id": 1426182,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849858504.873, "dur": 36.516, + "args": { + "External id": 1426183,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858506.611, "dur": 2.100, + "args": { + "External id": 1426184,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858509.817, "dur": 0.362, + "args": { + "External id": 1426185,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858513.407, "dur": 0.475, + "args": { + "External id": 1426186,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858517.386, "dur": 2.753, + "args": { + "External id": 1426187,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858523.461, "dur": 0.390, + "args": { + "External id": 1426188,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858524.743, "dur": 0.446, + "args": { + "External id": 1426189,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858527.853, "dur": 0.353, + "args": { + "External id": 1426190,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858531.733, "dur": 0.349, + "args": { + "External id": 1426191,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849858532.972, "dur": 2.330, + "args": { + "External id": 1426192,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849858553.524, "dur": 39.084, + "args": { + "External id": 1426193,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849858663.594, "dur": 484.571, + "args": { + "External id": 1426194,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849858702.028, "dur": 439.581, + "args": { + "External id": 1426195,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12631, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849858716.050, "dur": 417.781, + "args": { + "External id": 1426196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849859179.305, "dur": 3.148, + "args": { + "External id": 1426197,"Record function id": 0, "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": 12633, "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": 2338706, "tid": 2338706, + "ts": 6413849859298.674, "dur": 33886.200, + "args": { + "External id": 1426198,"Record function id": 0, "Ev Idx": 12634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859425.452, "dur": 8.752, + "args": { + "External id": 1426199,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859439.085, "dur": 1.362, + "args": { + "External id": 1426200,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859442.523, "dur": 3.713, + "args": { + "External id": 1426201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859450.554, "dur": 1.104, + "args": { + "External id": 1426202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859453.221, "dur": 0.971, + "args": { + "External id": 1426203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859455.850, "dur": 0.812, + "args": { + "External id": 1426204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859458.260, "dur": 1.186, + "args": { + "External id": 1426205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859466.300, "dur": 2.268, + "args": { + "External id": 1426206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859470.158, "dur": 0.854, + "args": { + "External id": 1426207,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849859472.414, "dur": 0.824, + "args": { + "External id": 1426208,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849859494.041, "dur": 33628.468, + "args": { + "External id": 1426209,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849859513.466, "dur": 33597.107, + "args": { + "External id": 1426210,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849859532.378, "dur": 18.072, + "args": { + "External id": 1426211,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849859554.428, "dur": 33480.465, + "args": { + "External id": 1426212,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849859557.128, "dur": 33476.969, + "args": { + "External id": 1426213,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849859562.272, "dur": 5.635, + "args": { + "External id": 1426214,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849859569.822, "dur": 33459.041, + "args": { + "External id": 1426215,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849893371.335, "dur": 45.708, + "args": { + "External id": 1426216,"Sequence number": 15348673, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12652 + } + }, + { + "ph": "s", "id": 209, "pid": 2338706, "tid": 2338706, "ts": 6413849893371.335, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849893394.803, "dur": 15.637, + "args": { + "External id": 1426217,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849893402.983, "dur": 7.166, + "args": { + "External id": 1426218,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849893506.535, "dur": 85.643, + "args": { + "External id": 1426219,"Record function id": 0, "Ev Idx": 12655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849893594.083, "dur": 1347.129, + "args": { + "External id": 1426220,"Record function id": 0, "Ev Idx": 12656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849893642.033, "dur": 1283.477, + "args": { + "External id": 1426221,"Sequence number": 15348674, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12657 + } + }, + { + "ph": "s", "id": 208, "pid": 2338706, "tid": 2338706, "ts": 6413849893642.033, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849893724.385, "dur": 57.419, + "args": { + "External id": 1426222,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849893797.599, "dur": 117.999, + "args": { + "External id": 1426223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849893932.928, "dur": 64.081, + "args": { + "External id": 1426224,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849894012.607, "dur": 39.139, + "args": { + "External id": 1426225,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849894128.701, "dur": 37.694, + "args": { + "External id": 1426226,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849894195.909, "dur": 22.255, + "args": { + "External id": 1426227,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849894248.615, "dur": 179.300, + "args": { + "External id": 1426228,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849894315.924, "dur": 14.537, + "args": { + "External id": 1426229,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849894322.611, "dur": 6.754, + "args": { + "External id": 1426230,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849894334.558, "dur": 4.333, + "args": { + "External id": 1426231,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849894348.796, "dur": 1.089, + "args": { + "External id": 1426232,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849894355.498, "dur": 5.835, + "args": { + "External id": 1426233,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849894442.229, "dur": 66.185, + "args": { + "External id": 1426234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849894549.995, "dur": 35.397, + "args": { + "External id": 1426235,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849894599.540, "dur": 53.471, + "args": { + "External id": 1426236,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849894660.375, "dur": 40.365, + "args": { + "External id": 1426237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849894723.956, "dur": 36.189, + "args": { + "External id": 1426238,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849894766.781, "dur": 40.533, + "args": { + "External id": 1426239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849894829.491, "dur": 19.438, + "args": { + "External id": 1426240,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12676 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 2338706, "tid": 2338706, + "ts": 6413849895036.891, "dur": 181.729, + "args": { + "External id": 1426241,"Record function id": 0, "Ev Idx": 12677 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849895326.015, "dur": 61.921, + "args": { + "External id": 1426242,"Record function id": 0, "Ev Idx": 12678 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338706, "tid": 2338706, + "ts": 6413849895399.804, "dur": 31759.287, + "args": { + "External id": 1426243,"Record function id": 0, "Ev Idx": 12679 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338706, "tid": 2338706, + "ts": 6413849895413.579, "dur": 1139.418, + "args": { + "External id": 1426244,"Record function id": 0, "Ev Idx": 12680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849895515.270, "dur": 13.107, + "args": { + "External id": 1426245,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849895546.189, "dur": 44.620, + "args": { + "External id": 1426246,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895554.741, "dur": 2.612, + "args": { + "External id": 1426247,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895560.895, "dur": 0.540, + "args": { + "External id": 1426248,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895564.827, "dur": 0.531, + "args": { + "External id": 1426249,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895566.135, "dur": 0.701, + "args": { + "External id": 1426250,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895568.754, "dur": 0.655, + "args": { + "External id": 1426251,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895572.546, "dur": 0.776, + "args": { + "External id": 1426252,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895573.954, "dur": 4.514, + "args": { + "External id": 1426253,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895579.474, "dur": 0.442, + "args": { + "External id": 1426254,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895582.930, "dur": 0.366, + "args": { + "External id": 1426255,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849895604.222, "dur": 71.932, + "args": { + "External id": 1426256,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849895715.772, "dur": 144.716, + "args": { + "External id": 1426257,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849895732.960, "dur": 4.974, + "args": { + "External id": 1426258,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849895746.857, "dur": 10.987, + "args": { + "External id": 1426259,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849895751.822, "dur": 5.520, + "args": { + "External id": 1426260,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895755.035, "dur": 0.676, + "args": { + "External id": 1426261,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849895765.237, "dur": 35.859, + "args": { + "External id": 1426262,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895769.436, "dur": 2.062, + "args": { + "External id": 1426263,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895772.444, "dur": 0.499, + "args": { + "External id": 1426264,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895773.733, "dur": 0.550, + "args": { + "External id": 1426265,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895779.332, "dur": 2.660, + "args": { + "External id": 1426266,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895782.790, "dur": 0.519, + "args": { + "External id": 1426267,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895784.162, "dur": 0.306, + "args": { + "External id": 1426268,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895789.197, "dur": 0.421, + "args": { + "External id": 1426269,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895790.264, "dur": 0.610, + "args": { + "External id": 1426270,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849895794.024, "dur": 2.291, + "args": { + "External id": 1426271,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849895812.279, "dur": 37.931, + "args": { + "External id": 1426272,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849895923.301, "dur": 512.883, + "args": { + "External id": 1426273,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849895963.901, "dur": 465.334, + "args": { + "External id": 1426274,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12710, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849895992.951, "dur": 426.379, + "args": { + "External id": 1426275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849896465.893, "dur": 2.651, + "args": { + "External id": 1426276,"Record function id": 0, "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": 12712, "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": 2338706, "tid": 2338706, + "ts": 6413849896577.605, "dur": 30272.885, + "args": { + "External id": 1426277,"Record function id": 0, "Ev Idx": 12713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896694.913, "dur": 6.785, + "args": { + "External id": 1426278,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896705.597, "dur": 1.385, + "args": { + "External id": 1426279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896708.987, "dur": 3.987, + "args": { + "External id": 1426280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896715.000, "dur": 1.508, + "args": { + "External id": 1426281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896718.232, "dur": 0.826, + "args": { + "External id": 1426282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896720.747, "dur": 1.080, + "args": { + "External id": 1426283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896728.365, "dur": 1.334, + "args": { + "External id": 1426284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896731.069, "dur": 2.377, + "args": { + "External id": 1426285,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896734.862, "dur": 0.589, + "args": { + "External id": 1426286,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849896737.121, "dur": 0.911, + "args": { + "External id": 1426287,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849896773.767, "dur": 30018.295, + "args": { + "External id": 1426288,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849896795.520, "dur": 29986.028, + "args": { + "External id": 1426289,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849896812.053, "dur": 17.469, + "args": { + "External id": 1426290,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849896833.556, "dur": 29902.808, + "args": { + "External id": 1426291,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849896836.487, "dur": 29899.037, + "args": { + "External id": 1426292,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849896842.040, "dur": 5.642, + "args": { + "External id": 1426293,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849896849.568, "dur": 29882.097, + "args": { + "External id": 1426294,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849927044.738, "dur": 78.192, + "args": { + "External id": 1426295,"Sequence number": 15348675, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12731 + } + }, + { + "ph": "s", "id": 207, "pid": 2338706, "tid": 2338706, "ts": 6413849927044.738, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849927097.725, "dur": 18.131, + "args": { + "External id": 1426296,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849927106.779, "dur": 8.600, + "args": { + "External id": 1426297,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849927213.047, "dur": 85.411, + "args": { + "External id": 1426298,"Record function id": 0, "Ev Idx": 12734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849927300.098, "dur": 1361.586, + "args": { + "External id": 1426299,"Record function id": 0, "Ev Idx": 12735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849927349.314, "dur": 1295.903, + "args": { + "External id": 1426300,"Sequence number": 15348676, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12736 + } + }, + { + "ph": "s", "id": 206, "pid": 2338706, "tid": 2338706, "ts": 6413849927349.314, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849927438.493, "dur": 69.240, + "args": { + "External id": 1426301,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849927526.046, "dur": 118.720, + "args": { + "External id": 1426302,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849927660.932, "dur": 48.409, + "args": { + "External id": 1426303,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849927722.229, "dur": 38.631, + "args": { + "External id": 1426304,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849927795.514, "dur": 35.329, + "args": { + "External id": 1426305,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849927856.363, "dur": 21.199, + "args": { + "External id": 1426306,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849927903.597, "dur": 224.199, + "args": { + "External id": 1426307,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849927961.744, "dur": 35.467, + "args": { + "External id": 1426308,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849927968.310, "dur": 26.589, + "args": { + "External id": 1426309,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849928003.418, "dur": 5.876, + "args": { + "External id": 1426310,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849928010.434, "dur": 1.328, + "args": { + "External id": 1426311,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849928015.726, "dur": 5.764, + "args": { + "External id": 1426312,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849928145.323, "dur": 70.571, + "args": { + "External id": 1426313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849928258.316, "dur": 37.674, + "args": { + "External id": 1426314,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849928309.705, "dur": 53.032, + "args": { + "External id": 1426315,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849928370.890, "dur": 40.261, + "args": { + "External id": 1426316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849928439.179, "dur": 32.282, + "args": { + "External id": 1426317,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849928479.879, "dur": 40.873, + "args": { + "External id": 1426318,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849928539.705, "dur": 21.001, + "args": { + "External id": 1426319,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12755 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 2338706, "tid": 2338706, + "ts": 6413849928743.304, "dur": 91.990, + "args": { + "External id": 1426320,"Record function id": 0, "Ev Idx": 12756 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849928923.132, "dur": 75.001, + "args": { + "External id": 1426321,"Record function id": 0, "Ev Idx": 12757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338706, "tid": 2338706, + "ts": 6413849929012.725, "dur": 33008.966, + "args": { + "External id": 1426322,"Record function id": 0, "Ev Idx": 12758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338706, "tid": 2338706, + "ts": 6413849929025.173, "dur": 1282.804, + "args": { + "External id": 1426323,"Record function id": 0, "Ev Idx": 12759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849929160.035, "dur": 12.318, + "args": { + "External id": 1426324,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849929194.718, "dur": 43.961, + "args": { + "External id": 1426325,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929200.740, "dur": 2.388, + "args": { + "External id": 1426326,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929206.846, "dur": 0.502, + "args": { + "External id": 1426327,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929210.580, "dur": 0.496, + "args": { + "External id": 1426328,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929211.925, "dur": 0.606, + "args": { + "External id": 1426329,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929215.109, "dur": 0.547, + "args": { + "External id": 1426330,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929218.239, "dur": 0.603, + "args": { + "External id": 1426331,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929219.454, "dur": 3.888, + "args": { + "External id": 1426332,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929225.555, "dur": 0.420, + "args": { + "External id": 1426333,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929226.764, "dur": 0.398, + "args": { + "External id": 1426334,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849929253.211, "dur": 66.512, + "args": { + "External id": 1426335,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849929366.357, "dur": 195.448, + "args": { + "External id": 1426336,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849929382.090, "dur": 4.481, + "args": { + "External id": 1426337,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849929392.654, "dur": 11.469, + "args": { + "External id": 1426338,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849929397.950, "dur": 5.691, + "args": { + "External id": 1426339,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929401.418, "dur": 1.003, + "args": { + "External id": 1426340,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849929411.782, "dur": 38.014, + "args": { + "External id": 1426341,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929415.204, "dur": 1.191, + "args": { + "External id": 1426342,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929422.314, "dur": 0.563, + "args": { + "External id": 1426343,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929423.929, "dur": 0.470, + "args": { + "External id": 1426344,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929428.356, "dur": 2.849, + "args": { + "External id": 1426345,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929431.968, "dur": 0.442, + "args": { + "External id": 1426346,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929434.817, "dur": 2.278, + "args": { + "External id": 1426347,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929437.740, "dur": 0.416, + "args": { + "External id": 1426348,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929439.016, "dur": 0.349, + "args": { + "External id": 1426349,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849929444.656, "dur": 0.562, + "args": { + "External id": 1426350,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849929505.535, "dur": 45.875, + "args": { + "External id": 1426351,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849929629.109, "dur": 551.457, + "args": { + "External id": 1426352,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849929667.404, "dur": 506.006, + "args": { + "External id": 1426353,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12789, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849929680.002, "dur": 485.080, + "args": { + "External id": 1426354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849930213.385, "dur": 2.999, + "args": { + "External id": 1426355,"Record function id": 0, "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": 12791, "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": 2338706, "tid": 2338706, + "ts": 6413849930333.849, "dur": 31409.166, + "args": { + "External id": 1426356,"Record function id": 0, "Ev Idx": 12792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930454.801, "dur": 7.805, + "args": { + "External id": 1426357,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930466.477, "dur": 1.140, + "args": { + "External id": 1426358,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930469.513, "dur": 3.584, + "args": { + "External id": 1426359,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930475.298, "dur": 0.996, + "args": { + "External id": 1426360,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930477.819, "dur": 0.948, + "args": { + "External id": 1426361,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930483.136, "dur": 0.998, + "args": { + "External id": 1426362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930485.696, "dur": 0.977, + "args": { + "External id": 1426363,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930488.666, "dur": 1.980, + "args": { + "External id": 1426364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930492.094, "dur": 0.733, + "args": { + "External id": 1426365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849930496.300, "dur": 0.883, + "args": { + "External id": 1426366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849930520.940, "dur": 31158.985, + "args": { + "External id": 1426367,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849930540.502, "dur": 31128.280, + "args": { + "External id": 1426368,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849930570.216, "dur": 20.317, + "args": { + "External id": 1426369,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849930594.786, "dur": 31029.144, + "args": { + "External id": 1426370,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849930598.934, "dur": 31024.010, + "args": { + "External id": 1426371,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849930604.582, "dur": 6.126, + "args": { + "External id": 1426372,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849930612.567, "dur": 31005.773, + "args": { + "External id": 1426373,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849961928.295, "dur": 42.183, + "args": { + "External id": 1426374,"Sequence number": 15348677, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12810 + } + }, + { + "ph": "s", "id": 205, "pid": 2338706, "tid": 2338706, "ts": 6413849961928.295, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849961951.945, "dur": 12.884, + "args": { + "External id": 1426375,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849961957.529, "dur": 7.034, + "args": { + "External id": 1426376,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849962104.562, "dur": 86.587, + "args": { + "External id": 1426377,"Record function id": 0, "Ev Idx": 12813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849962192.984, "dur": 1325.484, + "args": { + "External id": 1426378,"Record function id": 0, "Ev Idx": 12814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849962238.282, "dur": 1264.532, + "args": { + "External id": 1426379,"Sequence number": 15348678, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12815 + } + }, + { + "ph": "s", "id": 204, "pid": 2338706, "tid": 2338706, "ts": 6413849962238.282, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849962326.686, "dur": 61.084, + "args": { + "External id": 1426380,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849962405.153, "dur": 118.957, + "args": { + "External id": 1426381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849962544.284, "dur": 42.229, + "args": { + "External id": 1426382,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849962599.399, "dur": 34.278, + "args": { + "External id": 1426383,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849962664.770, "dur": 32.455, + "args": { + "External id": 1426384,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849962722.243, "dur": 22.424, + "args": { + "External id": 1426385,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849962770.450, "dur": 154.919, + "args": { + "External id": 1426386,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849962826.441, "dur": 16.706, + "args": { + "External id": 1426387,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849962835.055, "dur": 7.065, + "args": { + "External id": 1426388,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849962847.117, "dur": 4.384, + "args": { + "External id": 1426389,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849962852.828, "dur": 0.962, + "args": { + "External id": 1426390,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849962856.432, "dur": 6.405, + "args": { + "External id": 1426391,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849962939.915, "dur": 74.454, + "args": { + "External id": 1426392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849963093.074, "dur": 41.910, + "args": { + "External id": 1426393,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849963157.836, "dur": 55.010, + "args": { + "External id": 1426394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849963223.891, "dur": 40.454, + "args": { + "External id": 1426395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849963294.086, "dur": 35.098, + "args": { + "External id": 1426396,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849963337.647, "dur": 44.148, + "args": { + "External id": 1426397,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849963405.639, "dur": 22.847, + "args": { + "External id": 1426398,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 2338706, "tid": 2338706, + "ts": 6413849963593.326, "dur": 91.427, + "args": { + "External id": 1426399,"Record function id": 0, "Ev Idx": 12835 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849963771.850, "dur": 56.415, + "args": { + "External id": 1426400,"Record function id": 0, "Ev Idx": 12836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338706, "tid": 2338706, + "ts": 6413849963838.595, "dur": 31390.948, + "args": { + "External id": 1426401,"Record function id": 0, "Ev Idx": 12837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338706, "tid": 2338706, + "ts": 6413849963852.411, "dur": 1271.878, + "args": { + "External id": 1426402,"Record function id": 0, "Ev Idx": 12838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849963944.549, "dur": 9.763, + "args": { + "External id": 1426403,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849963969.805, "dur": 64.662, + "args": { + "External id": 1426404,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849963996.537, "dur": 3.805, + "args": { + "External id": 1426405,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964007.403, "dur": 0.501, + "args": { + "External id": 1426406,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964008.809, "dur": 0.489, + "args": { + "External id": 1426407,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964010.285, "dur": 0.627, + "args": { + "External id": 1426408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964015.547, "dur": 0.756, + "args": { + "External id": 1426409,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964017.073, "dur": 0.702, + "args": { + "External id": 1426410,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964020.527, "dur": 4.437, + "args": { + "External id": 1426411,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964025.896, "dur": 0.726, + "args": { + "External id": 1426412,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964027.273, "dur": 0.463, + "args": { + "External id": 1426413,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849964051.436, "dur": 104.634, + "args": { + "External id": 1426414,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849964203.894, "dur": 151.054, + "args": { + "External id": 1426415,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849964220.630, "dur": 6.753, + "args": { + "External id": 1426416,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849964236.139, "dur": 15.031, + "args": { + "External id": 1426417,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849964244.337, "dur": 6.317, + "args": { + "External id": 1426418,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964248.027, "dur": 0.740, + "args": { + "External id": 1426419,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849964261.676, "dur": 33.626, + "args": { + "External id": 1426420,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964263.674, "dur": 2.160, + "args": { + "External id": 1426421,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964266.716, "dur": 0.521, + "args": { + "External id": 1426422,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964270.577, "dur": 0.344, + "args": { + "External id": 1426423,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964273.174, "dur": 2.671, + "args": { + "External id": 1426424,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964279.545, "dur": 0.466, + "args": { + "External id": 1426425,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964280.746, "dur": 0.518, + "args": { + "External id": 1426426,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964283.275, "dur": 0.266, + "args": { + "External id": 1426427,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964287.042, "dur": 0.399, + "args": { + "External id": 1426428,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849964288.122, "dur": 2.033, + "args": { + "External id": 1426429,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849964308.525, "dur": 36.205, + "args": { + "External id": 1426430,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849964422.050, "dur": 524.503, + "args": { + "External id": 1426431,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849964459.784, "dur": 480.355, + "args": { + "External id": 1426432,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12868, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849964572.574, "dur": 361.848, + "args": { + "External id": 1426433,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849964994.927, "dur": 5.160, + "args": { + "External id": 1426434,"Record function id": 0, "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": 12870, "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": 2338706, "tid": 2338706, + "ts": 6413849965152.711, "dur": 29773.033, + "args": { + "External id": 1426435,"Record function id": 0, "Ev Idx": 12871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965278.308, "dur": 8.168, + "args": { + "External id": 1426436,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965290.766, "dur": 1.345, + "args": { + "External id": 1426437,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965293.817, "dur": 3.451, + "args": { + "External id": 1426438,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965299.562, "dur": 0.799, + "args": { + "External id": 1426439,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965302.033, "dur": 0.821, + "args": { + "External id": 1426440,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965304.329, "dur": 1.017, + "args": { + "External id": 1426441,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965309.499, "dur": 1.151, + "args": { + "External id": 1426442,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965312.428, "dur": 1.972, + "args": { + "External id": 1426443,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965316.077, "dur": 0.985, + "args": { + "External id": 1426444,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849965318.533, "dur": 0.864, + "args": { + "External id": 1426445,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849965345.474, "dur": 29522.735, + "args": { + "External id": 1426446,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849965364.522, "dur": 29492.739, + "args": { + "External id": 1426447,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849965387.006, "dur": 17.898, + "args": { + "External id": 1426448,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849965409.077, "dur": 29399.586, + "args": { + "External id": 1426449,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849965412.082, "dur": 29395.777, + "args": { + "External id": 1426450,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849965419.374, "dur": 5.816, + "args": { + "External id": 1426451,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849965427.472, "dur": 29375.444, + "args": { + "External id": 1426452,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849995158.154, "dur": 39.615, + "args": { + "External id": 1426453,"Sequence number": 15348679, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12889 + } + }, + { + "ph": "s", "id": 203, "pid": 2338706, "tid": 2338706, "ts": 6413849995158.154, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413849995178.662, "dur": 13.519, + "args": { + "External id": 1426454,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849995184.018, "dur": 7.680, + "args": { + "External id": 1426455,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413849995277.528, "dur": 82.737, + "args": { + "External id": 1426456,"Record function id": 0, "Ev Idx": 12892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413849995361.900, "dur": 1322.283, + "args": { + "External id": 1426457,"Record function id": 0, "Ev Idx": 12893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413849995411.440, "dur": 1255.265, + "args": { + "External id": 1426458,"Sequence number": 15348680, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12894 + } + }, + { + "ph": "s", "id": 202, "pid": 2338706, "tid": 2338706, "ts": 6413849995411.440, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849995496.435, "dur": 62.921, + "args": { + "External id": 1426459,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849995575.737, "dur": 120.747, + "args": { + "External id": 1426460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849995713.057, "dur": 42.911, + "args": { + "External id": 1426461,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849995768.186, "dur": 33.675, + "args": { + "External id": 1426462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849995832.061, "dur": 32.136, + "args": { + "External id": 1426463,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413849995888.271, "dur": 19.864, + "args": { + "External id": 1426464,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413849995931.807, "dur": 222.592, + "args": { + "External id": 1426465,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413849996012.529, "dur": 16.966, + "args": { + "External id": 1426466,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849996021.505, "dur": 6.684, + "args": { + "External id": 1426467,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849996032.326, "dur": 4.572, + "args": { + "External id": 1426468,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849996038.302, "dur": 1.512, + "args": { + "External id": 1426469,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849996042.576, "dur": 5.214, + "args": { + "External id": 1426470,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849996170.187, "dur": 63.826, + "args": { + "External id": 1426471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413849996274.072, "dur": 39.044, + "args": { + "External id": 1426472,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849996326.589, "dur": 51.469, + "args": { + "External id": 1426473,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849996387.809, "dur": 41.048, + "args": { + "External id": 1426474,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413849996455.764, "dur": 31.700, + "args": { + "External id": 1426475,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413849996498.254, "dur": 45.239, + "args": { + "External id": 1426476,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413849996568.906, "dur": 21.820, + "args": { + "External id": 1426477,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12913 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 2338706, "tid": 2338706, + "ts": 6413849996759.592, "dur": 88.731, + "args": { + "External id": 1426478,"Record function id": 0, "Ev Idx": 12914 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413849996936.672, "dur": 78.885, + "args": { + "External id": 1426479,"Record function id": 0, "Ev Idx": 12915 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338706, "tid": 2338706, + "ts": 6413849997028.212, "dur": 32442.535, + "args": { + "External id": 1426480,"Record function id": 0, "Ev Idx": 12916 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338706, "tid": 2338706, + "ts": 6413849997040.626, "dur": 1130.386, + "args": { + "External id": 1426481,"Record function id": 0, "Ev Idx": 12917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849997179.850, "dur": 11.854, + "args": { + "External id": 1426482,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849997207.659, "dur": 44.669, + "args": { + "External id": 1426483,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997213.919, "dur": 2.835, + "args": { + "External id": 1426484,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997223.669, "dur": 0.501, + "args": { + "External id": 1426485,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997225.080, "dur": 0.599, + "args": { + "External id": 1426486,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997228.749, "dur": 0.655, + "args": { + "External id": 1426487,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997232.511, "dur": 0.579, + "args": { + "External id": 1426488,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997233.848, "dur": 0.704, + "args": { + "External id": 1426489,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997237.788, "dur": 4.266, + "args": { + "External id": 1426490,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997243.081, "dur": 0.275, + "args": { + "External id": 1426491,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997244.677, "dur": 0.497, + "args": { + "External id": 1426492,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849997270.147, "dur": 64.454, + "args": { + "External id": 1426493,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413849997376.177, "dur": 144.364, + "args": { + "External id": 1426494,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 12930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849997391.396, "dur": 6.007, + "args": { + "External id": 1426495,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413849997403.343, "dur": 14.698, + "args": { + "External id": 1426496,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413849997408.583, "dur": 8.926, + "args": { + "External id": 1426497,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 12933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997414.915, "dur": 1.148, + "args": { + "External id": 1426498,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 12934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413849997424.925, "dur": 31.134, + "args": { + "External id": 1426499,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997426.740, "dur": 0.463, + "args": { + "External id": 1426500,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997430.543, "dur": 2.044, + "args": { + "External id": 1426501,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997433.468, "dur": 0.535, + "args": { + "External id": 1426502,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997434.872, "dur": 3.215, + "args": { + "External id": 1426503,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997443.510, "dur": 0.349, + "args": { + "External id": 1426504,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997444.924, "dur": 0.625, + "args": { + "External id": 1426505,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997446.111, "dur": 0.580, + "args": { + "External id": 1426506,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997450.061, "dur": 0.336, + "args": { + "External id": 1426507,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849997451.283, "dur": 0.428, + "args": { + "External id": 1426508,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849997472.188, "dur": 38.971, + "args": { + "External id": 1426509,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 12945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413849997583.185, "dur": 428.951, + "args": { + "External id": 1426510,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 12946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849997619.249, "dur": 386.766, + "args": { + "External id": 1426511,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 12947, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413849997630.867, "dur": 367.293, + "args": { + "External id": 1426512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 12948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413849998042.815, "dur": 3.193, + "args": { + "External id": 1426513,"Record function id": 0, "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": 12949, "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": 2338706, "tid": 2338706, + "ts": 6413849998196.421, "dur": 31002.440, + "args": { + "External id": 1426514,"Record function id": 0, "Ev Idx": 12950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998323.521, "dur": 7.353, + "args": { + "External id": 1426515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 12951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998334.657, "dur": 1.266, + "args": { + "External id": 1426516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998337.851, "dur": 4.266, + "args": { + "External id": 1426517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998344.226, "dur": 0.899, + "args": { + "External id": 1426518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998346.655, "dur": 1.231, + "args": { + "External id": 1426519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 12955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998349.555, "dur": 0.947, + "args": { + "External id": 1426520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 12956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998354.245, "dur": 1.215, + "args": { + "External id": 1426521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 12957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998357.200, "dur": 2.224, + "args": { + "External id": 1426522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998360.932, "dur": 0.844, + "args": { + "External id": 1426523,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413849998365.491, "dur": 0.625, + "args": { + "External id": 1426524,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 12960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849998389.188, "dur": 30744.144, + "args": { + "External id": 1426525,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849998407.905, "dur": 30714.008, + "args": { + "External id": 1426526,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 12962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413849998428.521, "dur": 20.309, + "args": { + "External id": 1426527,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413849998452.821, "dur": 30591.426, + "args": { + "External id": 1426528,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 12964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413849998455.971, "dur": 30587.529, + "args": { + "External id": 1426529,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 12965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413849998462.852, "dur": 5.811, + "args": { + "External id": 1426530,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413849998470.496, "dur": 30567.836, + "args": { + "External id": 1426531,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 12967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850029392.058, "dur": 44.870, + "args": { + "External id": 1426532,"Sequence number": 15348681, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 12968 + } + }, + { + "ph": "s", "id": 201, "pid": 2338706, "tid": 2338706, "ts": 6413850029392.058, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850029416.838, "dur": 13.143, + "args": { + "External id": 1426533,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 12969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850029422.433, "dur": 7.284, + "args": { + "External id": 1426534,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 12970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850029524.783, "dur": 85.520, + "args": { + "External id": 1426535,"Record function id": 0, "Ev Idx": 12971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850029614.033, "dur": 1355.825, + "args": { + "External id": 1426536,"Record function id": 0, "Ev Idx": 12972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850029664.234, "dur": 1288.994, + "args": { + "External id": 1426537,"Sequence number": 15348682, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 12973 + } + }, + { + "ph": "s", "id": 200, "pid": 2338706, "tid": 2338706, "ts": 6413850029664.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850029751.097, "dur": 62.003, + "args": { + "External id": 1426538,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850029831.511, "dur": 120.924, + "args": { + "External id": 1426539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850029968.459, "dur": 73.190, + "args": { + "External id": 1426540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850030097.819, "dur": 45.034, + "args": { + "External id": 1426541,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 12977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850030181.002, "dur": 34.144, + "args": { + "External id": 1426542,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850030241.161, "dur": 23.896, + "args": { + "External id": 1426543,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 12979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850030293.535, "dur": 157.083, + "args": { + "External id": 1426544,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 12980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850030354.492, "dur": 15.666, + "args": { + "External id": 1426545,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 12981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850030361.653, "dur": 7.543, + "args": { + "External id": 1426546,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850030374.117, "dur": 4.271, + "args": { + "External id": 1426547,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850030379.729, "dur": 1.195, + "args": { + "External id": 1426548,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850030383.756, "dur": 5.480, + "args": { + "External id": 1426549,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850030465.017, "dur": 58.820, + "args": { + "External id": 1426550,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 12986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850030565.963, "dur": 36.285, + "args": { + "External id": 1426551,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 12987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850030612.230, "dur": 52.390, + "args": { + "External id": 1426552,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850030674.183, "dur": 41.323, + "args": { + "External id": 1426553,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 12989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850030741.151, "dur": 33.294, + "args": { + "External id": 1426554,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 12990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850030782.684, "dur": 42.307, + "args": { + "External id": 1426555,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 12991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850030846.106, "dur": 24.026, + "args": { + "External id": 1426556,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 12992 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 2338706, "tid": 2338706, + "ts": 6413850031115.091, "dur": 96.666, + "args": { + "External id": 1426557,"Record function id": 0, "Ev Idx": 12993 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850031303.031, "dur": 56.462, + "args": { + "External id": 1426558,"Record function id": 0, "Ev Idx": 12994 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338706, "tid": 2338706, + "ts": 6413850031369.498, "dur": 29432.215, + "args": { + "External id": 1426559,"Record function id": 0, "Ev Idx": 12995 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338706, "tid": 2338706, + "ts": 6413850031383.167, "dur": 1115.928, + "args": { + "External id": 1426560,"Record function id": 0, "Ev Idx": 12996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850031476.955, "dur": 11.375, + "args": { + "External id": 1426561,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850031507.387, "dur": 42.188, + "args": { + "External id": 1426562,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 12998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031514.848, "dur": 2.570, + "args": { + "External id": 1426563,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 12999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031520.698, "dur": 0.485, + "args": { + "External id": 1426564,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031522.132, "dur": 0.541, + "args": { + "External id": 1426565,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031525.781, "dur": 2.102, + "args": { + "External id": 1426566,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031528.773, "dur": 0.668, + "args": { + "External id": 1426567,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031531.748, "dur": 0.426, + "args": { + "External id": 1426568,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031534.703, "dur": 2.998, + "args": { + "External id": 1426569,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031538.635, "dur": 0.563, + "args": { + "External id": 1426570,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031542.346, "dur": 0.403, + "args": { + "External id": 1426571,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850031562.200, "dur": 67.099, + "args": { + "External id": 1426572,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850031666.050, "dur": 146.308, + "args": { + "External id": 1426573,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850031681.915, "dur": 4.199, + "args": { + "External id": 1426574,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850031694.798, "dur": 13.983, + "args": { + "External id": 1426575,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850031699.654, "dur": 8.614, + "args": { + "External id": 1426576,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031704.765, "dur": 2.161, + "args": { + "External id": 1426577,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850031717.016, "dur": 30.500, + "args": { + "External id": 1426578,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031718.891, "dur": 0.441, + "args": { + "External id": 1426579,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031722.506, "dur": 0.678, + "args": { + "External id": 1426580,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031724.133, "dur": 0.532, + "args": { + "External id": 1426581,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031728.048, "dur": 2.896, + "args": { + "External id": 1426582,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031731.717, "dur": 0.935, + "args": { + "External id": 1426583,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031733.424, "dur": 0.640, + "args": { + "External id": 1426584,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031737.328, "dur": 0.527, + "args": { + "External id": 1426585,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031738.929, "dur": 0.519, + "args": { + "External id": 1426586,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850031742.232, "dur": 0.343, + "args": { + "External id": 1426587,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850031761.495, "dur": 41.153, + "args": { + "External id": 1426588,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850031873.429, "dur": 506.305, + "args": { + "External id": 1426589,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850031911.923, "dur": 460.820, + "args": { + "External id": 1426590,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13026, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850031922.695, "dur": 442.980, + "args": { + "External id": 1426591,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850032409.658, "dur": 2.973, + "args": { + "External id": 1426592,"Record function id": 0, "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": 13028, "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": 2338706, "tid": 2338706, + "ts": 6413850032524.462, "dur": 28005.044, + "args": { + "External id": 1426593,"Record function id": 0, "Ev Idx": 13029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032645.074, "dur": 7.262, + "args": { + "External id": 1426594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032656.080, "dur": 1.305, + "args": { + "External id": 1426595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032659.490, "dur": 3.995, + "args": { + "External id": 1426596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032665.574, "dur": 1.088, + "args": { + "External id": 1426597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032668.436, "dur": 1.055, + "args": { + "External id": 1426598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032670.963, "dur": 1.144, + "args": { + "External id": 1426599,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032676.256, "dur": 1.240, + "args": { + "External id": 1426600,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032681.066, "dur": 2.237, + "args": { + "External id": 1426601,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032685.300, "dur": 0.851, + "args": { + "External id": 1426602,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850032687.837, "dur": 0.714, + "args": { + "External id": 1426603,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850032709.565, "dur": 27753.743, + "args": { + "External id": 1426604,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850032729.793, "dur": 27722.157, + "args": { + "External id": 1426605,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850032750.303, "dur": 18.393, + "args": { + "External id": 1426606,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850032772.590, "dur": 27630.720, + "args": { + "External id": 1426607,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850032775.503, "dur": 27626.194, + "args": { + "External id": 1426608,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850032781.333, "dur": 5.891, + "args": { + "External id": 1426609,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850032789.418, "dur": 27608.311, + "args": { + "External id": 1426610,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850060720.599, "dur": 42.722, + "args": { + "External id": 1426611,"Sequence number": 15348683, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13047 + } + }, + { + "ph": "s", "id": 199, "pid": 2338706, "tid": 2338706, "ts": 6413850060720.599, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850060741.280, "dur": 16.564, + "args": { + "External id": 1426612,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850060748.926, "dur": 7.415, + "args": { + "External id": 1426613,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850060857.869, "dur": 86.255, + "args": { + "External id": 1426614,"Record function id": 0, "Ev Idx": 13050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850060946.037, "dur": 1382.817, + "args": { + "External id": 1426615,"Record function id": 0, "Ev Idx": 13051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850061010.642, "dur": 1302.377, + "args": { + "External id": 1426616,"Sequence number": 15348684, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13052 + } + }, + { + "ph": "s", "id": 198, "pid": 2338706, "tid": 2338706, "ts": 6413850061010.642, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850061133.503, "dur": 61.323, + "args": { + "External id": 1426617,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850061213.231, "dur": 117.266, + "args": { + "External id": 1426618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850061347.932, "dur": 44.337, + "args": { + "External id": 1426619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850061404.470, "dur": 35.035, + "args": { + "External id": 1426620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850061468.307, "dur": 33.240, + "args": { + "External id": 1426621,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850061528.653, "dur": 22.398, + "args": { + "External id": 1426622,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850061577.128, "dur": 152.941, + "args": { + "External id": 1426623,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850061632.369, "dur": 14.956, + "args": { + "External id": 1426624,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850061639.222, "dur": 7.205, + "args": { + "External id": 1426625,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850061651.254, "dur": 4.780, + "args": { + "External id": 1426626,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850061659.198, "dur": 1.186, + "args": { + "External id": 1426627,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850061663.131, "dur": 4.817, + "args": { + "External id": 1426628,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850061744.175, "dur": 61.841, + "args": { + "External id": 1426629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850061847.282, "dur": 35.002, + "args": { + "External id": 1426630,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850061894.126, "dur": 51.944, + "args": { + "External id": 1426631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850061954.596, "dur": 60.137, + "args": { + "External id": 1426632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850062087.545, "dur": 40.286, + "args": { + "External id": 1426633,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850062138.150, "dur": 52.296, + "args": { + "External id": 1426634,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850062213.209, "dur": 25.234, + "args": { + "External id": 1426635,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13071 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 2338706, "tid": 2338706, + "ts": 6413850062403.645, "dur": 90.046, + "args": { + "External id": 1426636,"Record function id": 0, "Ev Idx": 13072 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850062582.359, "dur": 55.506, + "args": { + "External id": 1426637,"Record function id": 0, "Ev Idx": 13073 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338706, "tid": 2338706, + "ts": 6413850062648.243, "dur": 31381.303, + "args": { + "External id": 1426638,"Record function id": 0, "Ev Idx": 13074 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338706, "tid": 2338706, + "ts": 6413850062658.867, "dur": 1122.292, + "args": { + "External id": 1426639,"Record function id": 0, "Ev Idx": 13075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850062752.614, "dur": 11.032, + "args": { + "External id": 1426640,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850062780.571, "dur": 43.143, + "args": { + "External id": 1426641,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062788.095, "dur": 2.289, + "args": { + "External id": 1426642,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062794.720, "dur": 0.511, + "args": { + "External id": 1426643,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062797.635, "dur": 0.438, + "args": { + "External id": 1426644,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062798.991, "dur": 0.560, + "args": { + "External id": 1426645,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062802.898, "dur": 0.572, + "args": { + "External id": 1426646,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062806.591, "dur": 0.435, + "args": { + "External id": 1426647,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062807.733, "dur": 4.192, + "args": { + "External id": 1426648,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062812.905, "dur": 0.519, + "args": { + "External id": 1426649,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062816.191, "dur": 0.288, + "args": { + "External id": 1426650,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850062836.138, "dur": 64.308, + "args": { + "External id": 1426651,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850062938.926, "dur": 239.521, + "args": { + "External id": 1426652,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850062955.778, "dur": 4.035, + "args": { + "External id": 1426653,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850062965.706, "dur": 35.893, + "args": { + "External id": 1426654,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850062970.788, "dur": 30.132, + "args": { + "External id": 1426655,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850062995.933, "dur": 1.166, + "args": { + "External id": 1426656,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850063011.197, "dur": 31.458, + "args": { + "External id": 1426657,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063014.896, "dur": 2.010, + "args": { + "External id": 1426658,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063017.985, "dur": 0.349, + "args": { + "External id": 1426659,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063019.160, "dur": 0.405, + "args": { + "External id": 1426660,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063023.813, "dur": 2.812, + "args": { + "External id": 1426661,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063027.229, "dur": 0.471, + "args": { + "External id": 1426662,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063028.332, "dur": 0.404, + "args": { + "External id": 1426663,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063030.375, "dur": 0.710, + "args": { + "External id": 1426664,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063031.973, "dur": 0.480, + "args": { + "External id": 1426665,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850063035.564, "dur": 2.115, + "args": { + "External id": 1426666,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850063102.176, "dur": 58.953, + "args": { + "External id": 1426667,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850063255.533, "dur": 419.026, + "args": { + "External id": 1426668,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850063296.980, "dur": 371.378, + "args": { + "External id": 1426669,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13105, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850063308.887, "dur": 353.632, + "args": { + "External id": 1426670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850063698.221, "dur": 2.395, + "args": { + "External id": 1426671,"Record function id": 0, "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": 13107, "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": 2338706, "tid": 2338706, + "ts": 6413850063805.231, "dur": 29948.265, + "args": { + "External id": 1426672,"Record function id": 0, "Ev Idx": 13108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063919.181, "dur": 7.868, + "args": { + "External id": 1426673,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063930.911, "dur": 1.039, + "args": { + "External id": 1426674,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063934.201, "dur": 3.567, + "args": { + "External id": 1426675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063939.746, "dur": 1.205, + "args": { + "External id": 1426676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063942.608, "dur": 1.193, + "args": { + "External id": 1426677,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063945.531, "dur": 0.925, + "args": { + "External id": 1426678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063950.784, "dur": 0.824, + "args": { + "External id": 1426679,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063953.381, "dur": 2.272, + "args": { + "External id": 1426680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063956.997, "dur": 0.774, + "args": { + "External id": 1426681,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850063959.129, "dur": 0.895, + "args": { + "External id": 1426682,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850064005.206, "dur": 29682.453, + "args": { + "External id": 1426683,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850064027.816, "dur": 29648.369, + "args": { + "External id": 1426684,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850064049.320, "dur": 56.585, + "args": { + "External id": 1426685,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850064112.850, "dur": 29516.952, + "args": { + "External id": 1426686,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850064115.950, "dur": 29513.096, + "args": { + "External id": 1426687,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850064121.980, "dur": 7.448, + "args": { + "External id": 1426688,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850064131.322, "dur": 29492.884, + "args": { + "External id": 1426689,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850093934.899, "dur": 58.234, + "args": { + "External id": 1426690,"Sequence number": 15348685, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13126 + } + }, + { + "ph": "s", "id": 197, "pid": 2338706, "tid": 2338706, "ts": 6413850093934.899, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850093956.856, "dur": 14.709, + "args": { + "External id": 1426691,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850093964.408, "dur": 6.887, + "args": { + "External id": 1426692,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850094108.230, "dur": 89.190, + "args": { + "External id": 1426693,"Record function id": 0, "Ev Idx": 13129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850094199.107, "dur": 1351.363, + "args": { + "External id": 1426694,"Record function id": 0, "Ev Idx": 13130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850094246.713, "dur": 1283.259, + "args": { + "External id": 1426695,"Sequence number": 15348686, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13131 + } + }, + { + "ph": "s", "id": 196, "pid": 2338706, "tid": 2338706, "ts": 6413850094246.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850094331.012, "dur": 62.155, + "args": { + "External id": 1426696,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850094411.054, "dur": 117.672, + "args": { + "External id": 1426697,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850094544.524, "dur": 41.815, + "args": { + "External id": 1426698,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850094596.332, "dur": 34.336, + "args": { + "External id": 1426699,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850094667.675, "dur": 33.447, + "args": { + "External id": 1426700,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850094726.176, "dur": 20.500, + "args": { + "External id": 1426701,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850094773.392, "dur": 158.855, + "args": { + "External id": 1426702,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850094831.420, "dur": 14.311, + "args": { + "External id": 1426703,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850094837.932, "dur": 6.883, + "args": { + "External id": 1426704,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850094851.136, "dur": 6.748, + "args": { + "External id": 1426705,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850094859.258, "dur": 1.064, + "args": { + "External id": 1426706,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850094864.200, "dur": 6.244, + "args": { + "External id": 1426707,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850094946.518, "dur": 80.950, + "args": { + "External id": 1426708,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850095126.843, "dur": 43.441, + "args": { + "External id": 1426709,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850095186.286, "dur": 59.220, + "args": { + "External id": 1426710,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850095255.969, "dur": 41.502, + "args": { + "External id": 1426711,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850095326.568, "dur": 31.529, + "args": { + "External id": 1426712,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850095367.164, "dur": 40.500, + "args": { + "External id": 1426713,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850095427.293, "dur": 20.349, + "args": { + "External id": 1426714,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13150 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 2338706, "tid": 2338706, + "ts": 6413850095630.696, "dur": 91.532, + "args": { + "External id": 1426715,"Record function id": 0, "Ev Idx": 13151 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850095813.310, "dur": 55.505, + "args": { + "External id": 1426716,"Record function id": 0, "Ev Idx": 13152 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338706, "tid": 2338706, + "ts": 6413850095879.786, "dur": 32955.942, + "args": { + "External id": 1426717,"Record function id": 0, "Ev Idx": 13153 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338706, "tid": 2338706, + "ts": 6413850095892.466, "dur": 1219.284, + "args": { + "External id": 1426718,"Record function id": 0, "Ev Idx": 13154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850096009.829, "dur": 11.878, + "args": { + "External id": 1426719,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850096040.188, "dur": 91.746, + "args": { + "External id": 1426720,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096051.251, "dur": 39.816, + "args": { + "External id": 1426721,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096098.059, "dur": 0.685, + "args": { + "External id": 1426722,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096100.904, "dur": 0.427, + "args": { + "External id": 1426723,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096102.510, "dur": 2.394, + "args": { + "External id": 1426724,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096107.378, "dur": 0.582, + "args": { + "External id": 1426725,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096112.338, "dur": 0.420, + "args": { + "External id": 1426726,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096116.116, "dur": 2.623, + "args": { + "External id": 1426727,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096120.694, "dur": 0.446, + "args": { + "External id": 1426728,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096122.815, "dur": 1.906, + "args": { + "External id": 1426729,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850096146.792, "dur": 67.810, + "args": { + "External id": 1426730,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850096258.263, "dur": 144.938, + "args": { + "External id": 1426731,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850096273.529, "dur": 5.814, + "args": { + "External id": 1426732,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850096285.939, "dur": 12.251, + "args": { + "External id": 1426733,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850096290.883, "dur": 6.807, + "args": { + "External id": 1426734,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096295.511, "dur": 0.854, + "args": { + "External id": 1426735,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850096306.056, "dur": 34.136, + "args": { + "External id": 1426736,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096308.610, "dur": 0.584, + "args": { + "External id": 1426737,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096311.013, "dur": 0.738, + "args": { + "External id": 1426738,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096313.452, "dur": 2.446, + "args": { + "External id": 1426739,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096317.595, "dur": 3.034, + "args": { + "External id": 1426740,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096322.469, "dur": 0.590, + "args": { + "External id": 1426741,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096326.966, "dur": 0.417, + "args": { + "External id": 1426742,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096328.970, "dur": 0.484, + "args": { + "External id": 1426743,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096331.437, "dur": 0.374, + "args": { + "External id": 1426744,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850096335.375, "dur": 0.283, + "args": { + "External id": 1426745,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850096353.634, "dur": 39.936, + "args": { + "External id": 1426746,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850096472.610, "dur": 466.729, + "args": { + "External id": 1426747,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850096509.593, "dur": 422.820, + "args": { + "External id": 1426748,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13184, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850096521.552, "dur": 405.166, + "args": { + "External id": 1426749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850096967.100, "dur": 2.725, + "args": { + "External id": 1426750,"Record function id": 0, "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": 13186, "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": 2338706, "tid": 2338706, + "ts": 6413850097139.575, "dur": 31421.886, + "args": { + "External id": 1426751,"Record function id": 0, "Ev Idx": 13187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097266.491, "dur": 8.249, + "args": { + "External id": 1426752,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097279.789, "dur": 1.414, + "args": { + "External id": 1426753,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097283.638, "dur": 3.571, + "args": { + "External id": 1426754,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097289.785, "dur": 0.742, + "args": { + "External id": 1426755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097292.863, "dur": 1.079, + "args": { + "External id": 1426756,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097296.031, "dur": 0.999, + "args": { + "External id": 1426757,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097298.871, "dur": 1.212, + "args": { + "External id": 1426758,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097302.152, "dur": 2.089, + "args": { + "External id": 1426759,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097306.308, "dur": 4.279, + "args": { + "External id": 1426760,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850097314.791, "dur": 0.848, + "args": { + "External id": 1426761,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850097336.246, "dur": 31156.856, + "args": { + "External id": 1426762,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850097355.968, "dur": 31125.580, + "args": { + "External id": 1426763,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850097377.171, "dur": 20.714, + "args": { + "External id": 1426764,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850097402.015, "dur": 31031.348, + "args": { + "External id": 1426765,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850097405.195, "dur": 31027.289, + "args": { + "External id": 1426766,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850097410.986, "dur": 5.540, + "args": { + "External id": 1426767,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850097418.431, "dur": 31008.982, + "args": { + "External id": 1426768,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850128757.299, "dur": 41.476, + "args": { + "External id": 1426769,"Sequence number": 15348687, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13205 + } + }, + { + "ph": "s", "id": 195, "pid": 2338706, "tid": 2338706, "ts": 6413850128757.299, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850128778.249, "dur": 14.719, + "args": { + "External id": 1426770,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850128784.132, "dur": 7.585, + "args": { + "External id": 1426771,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850128889.926, "dur": 105.117, + "args": { + "External id": 1426772,"Record function id": 0, "Ev Idx": 13208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850128998.692, "dur": 1408.741, + "args": { + "External id": 1426773,"Record function id": 0, "Ev Idx": 13209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850129051.158, "dur": 1339.414, + "args": { + "External id": 1426774,"Sequence number": 15348688, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13210 + } + }, + { + "ph": "s", "id": 194, "pid": 2338706, "tid": 2338706, "ts": 6413850129051.158, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850129185.143, "dur": 64.056, + "args": { + "External id": 1426775,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850129268.783, "dur": 119.470, + "args": { + "External id": 1426776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850129403.030, "dur": 42.013, + "args": { + "External id": 1426777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850129457.818, "dur": 33.694, + "args": { + "External id": 1426778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850129523.421, "dur": 33.672, + "args": { + "External id": 1426779,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850129581.356, "dur": 19.088, + "args": { + "External id": 1426780,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850129626.834, "dur": 174.894, + "args": { + "External id": 1426781,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850129693.618, "dur": 16.434, + "args": { + "External id": 1426782,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850129701.414, "dur": 7.670, + "args": { + "External id": 1426783,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850129714.561, "dur": 4.327, + "args": { + "External id": 1426784,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850129720.568, "dur": 1.350, + "args": { + "External id": 1426785,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850129726.919, "dur": 6.382, + "args": { + "External id": 1426786,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850129815.248, "dur": 58.601, + "args": { + "External id": 1426787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850129910.863, "dur": 36.720, + "args": { + "External id": 1426788,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850129959.240, "dur": 72.099, + "args": { + "External id": 1426789,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850130045.744, "dur": 90.347, + "args": { + "External id": 1426790,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850130169.146, "dur": 39.506, + "args": { + "External id": 1426791,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850130216.311, "dur": 48.111, + "args": { + "External id": 1426792,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850130288.697, "dur": 24.383, + "args": { + "External id": 1426793,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 2338706, "tid": 2338706, + "ts": 6413850130484.327, "dur": 98.995, + "args": { + "External id": 1426794,"Record function id": 0, "Ev Idx": 13230 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850130674.943, "dur": 56.019, + "args": { + "External id": 1426795,"Record function id": 0, "Ev Idx": 13231 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338706, "tid": 2338706, + "ts": 6413850130742.965, "dur": 32751.883, + "args": { + "External id": 1426796,"Record function id": 0, "Ev Idx": 13232 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338706, "tid": 2338706, + "ts": 6413850130751.743, "dur": 1167.740, + "args": { + "External id": 1426797,"Record function id": 0, "Ev Idx": 13233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850130846.464, "dur": 11.461, + "args": { + "External id": 1426798,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850130874.351, "dur": 45.880, + "args": { + "External id": 1426799,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130881.125, "dur": 2.950, + "args": { + "External id": 1426800,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130888.190, "dur": 0.651, + "args": { + "External id": 1426801,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130891.226, "dur": 0.668, + "args": { + "External id": 1426802,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130894.392, "dur": 0.599, + "args": { + "External id": 1426803,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130899.211, "dur": 0.644, + "args": { + "External id": 1426804,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130902.113, "dur": 0.540, + "args": { + "External id": 1426805,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130904.073, "dur": 4.272, + "args": { + "External id": 1426806,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130910.584, "dur": 0.307, + "args": { + "External id": 1426807,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850130912.765, "dur": 0.815, + "args": { + "External id": 1426808,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850130933.780, "dur": 84.179, + "args": { + "External id": 1426809,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850131102.491, "dur": 202.161, + "args": { + "External id": 1426810,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850131119.035, "dur": 7.062, + "args": { + "External id": 1426811,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850131132.700, "dur": 14.103, + "args": { + "External id": 1426812,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850131138.186, "dur": 8.128, + "args": { + "External id": 1426813,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131143.348, "dur": 0.985, + "args": { + "External id": 1426814,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850131155.854, "dur": 35.192, + "args": { + "External id": 1426815,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131159.165, "dur": 2.419, + "args": { + "External id": 1426816,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131163.126, "dur": 0.541, + "args": { + "External id": 1426817,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131165.268, "dur": 0.712, + "args": { + "External id": 1426818,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131169.519, "dur": 2.664, + "args": { + "External id": 1426819,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131173.745, "dur": 0.475, + "args": { + "External id": 1426820,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131175.778, "dur": 0.423, + "args": { + "External id": 1426821,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131179.944, "dur": 0.352, + "args": { + "External id": 1426822,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131181.990, "dur": 0.370, + "args": { + "External id": 1426823,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850131184.343, "dur": 2.073, + "args": { + "External id": 1426824,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850131249.816, "dur": 44.189, + "args": { + "External id": 1426825,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850131370.486, "dur": 437.367, + "args": { + "External id": 1426826,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850131409.676, "dur": 392.030, + "args": { + "External id": 1426827,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13263, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850131423.753, "dur": 370.729, + "args": { + "External id": 1426828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850131834.953, "dur": 2.869, + "args": { + "External id": 1426829,"Record function id": 0, "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": 13265, "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": 2338706, "tid": 2338706, + "ts": 6413850131944.595, "dur": 31278.330, + "args": { + "External id": 1426830,"Record function id": 0, "Ev Idx": 13266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132135.018, "dur": 8.494, + "args": { + "External id": 1426831,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132148.612, "dur": 1.370, + "args": { + "External id": 1426832,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132152.462, "dur": 3.667, + "args": { + "External id": 1426833,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132158.504, "dur": 0.744, + "args": { + "External id": 1426834,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132161.425, "dur": 1.026, + "args": { + "External id": 1426835,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132164.265, "dur": 1.009, + "args": { + "External id": 1426836,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132167.137, "dur": 0.968, + "args": { + "External id": 1426837,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132169.909, "dur": 2.618, + "args": { + "External id": 1426838,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132174.161, "dur": 1.140, + "args": { + "External id": 1426839,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850132179.153, "dur": 0.950, + "args": { + "External id": 1426840,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850132202.425, "dur": 30953.973, + "args": { + "External id": 1426841,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850132222.286, "dur": 30922.440, + "args": { + "External id": 1426842,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850132241.984, "dur": 18.157, + "args": { + "External id": 1426843,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850132263.980, "dur": 30828.583, + "args": { + "External id": 1426844,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850132266.978, "dur": 30824.042, + "args": { + "External id": 1426845,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850132273.479, "dur": 6.369, + "args": { + "External id": 1426846,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850132282.026, "dur": 30804.405, + "args": { + "External id": 1426847,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850163421.994, "dur": 43.158, + "args": { + "External id": 1426848,"Sequence number": 15348689, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13284 + } + }, + { + "ph": "s", "id": 193, "pid": 2338706, "tid": 2338706, "ts": 6413850163421.994, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850163445.954, "dur": 13.678, + "args": { + "External id": 1426849,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850163452.212, "dur": 7.217, + "args": { + "External id": 1426850,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850163543.208, "dur": 86.011, + "args": { + "External id": 1426851,"Record function id": 0, "Ev Idx": 13287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850163631.256, "dur": 1369.606, + "args": { + "External id": 1426852,"Record function id": 0, "Ev Idx": 13288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850163678.667, "dur": 1287.763, + "args": { + "External id": 1426853,"Sequence number": 15348690, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13289 + } + }, + { + "ph": "s", "id": 192, "pid": 2338706, "tid": 2338706, "ts": 6413850163678.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850163761.424, "dur": 59.119, + "args": { + "External id": 1426854,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850163836.625, "dur": 122.502, + "args": { + "External id": 1426855,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850163993.153, "dur": 57.165, + "args": { + "External id": 1426856,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850164108.256, "dur": 46.672, + "args": { + "External id": 1426857,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850164191.439, "dur": 34.736, + "args": { + "External id": 1426858,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850164252.401, "dur": 21.314, + "args": { + "External id": 1426859,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850164301.386, "dur": 159.236, + "args": { + "External id": 1426860,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850164358.959, "dur": 16.045, + "args": { + "External id": 1426861,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850164366.132, "dur": 7.919, + "args": { + "External id": 1426862,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850164379.282, "dur": 4.919, + "args": { + "External id": 1426863,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850164385.954, "dur": 1.522, + "args": { + "External id": 1426864,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850164390.878, "dur": 5.811, + "args": { + "External id": 1426865,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850164475.675, "dur": 60.214, + "args": { + "External id": 1426866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850164572.444, "dur": 34.935, + "args": { + "External id": 1426867,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850164619.263, "dur": 50.129, + "args": { + "External id": 1426868,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850164681.511, "dur": 40.908, + "args": { + "External id": 1426869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850164748.329, "dur": 33.315, + "args": { + "External id": 1426870,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850164790.766, "dur": 41.783, + "args": { + "External id": 1426871,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850164855.492, "dur": 23.185, + "args": { + "External id": 1426872,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13308 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 2338706, "tid": 2338706, + "ts": 6413850165118.185, "dur": 93.376, + "args": { + "External id": 1426873,"Record function id": 0, "Ev Idx": 13309 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850165307.864, "dur": 57.779, + "args": { + "External id": 1426874,"Record function id": 0, "Ev Idx": 13310 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338706, "tid": 2338706, + "ts": 6413850165376.310, "dur": 34065.333, + "args": { + "External id": 1426875,"Record function id": 0, "Ev Idx": 13311 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338706, "tid": 2338706, + "ts": 6413850165385.630, "dur": 1122.985, + "args": { + "External id": 1426876,"Record function id": 0, "Ev Idx": 13312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850165483.108, "dur": 11.218, + "args": { + "External id": 1426877,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850165511.740, "dur": 43.296, + "args": { + "External id": 1426878,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165517.959, "dur": 2.805, + "args": { + "External id": 1426879,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165525.579, "dur": 0.545, + "args": { + "External id": 1426880,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165528.014, "dur": 0.555, + "args": { + "External id": 1426881,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165530.428, "dur": 0.392, + "args": { + "External id": 1426882,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165534.356, "dur": 0.317, + "args": { + "External id": 1426883,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165536.613, "dur": 0.489, + "args": { + "External id": 1426884,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165538.786, "dur": 4.604, + "args": { + "External id": 1426885,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165545.500, "dur": 0.594, + "args": { + "External id": 1426886,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165547.582, "dur": 0.472, + "args": { + "External id": 1426887,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850165572.840, "dur": 67.740, + "args": { + "External id": 1426888,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850165679.128, "dur": 138.735, + "args": { + "External id": 1426889,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850165692.256, "dur": 6.239, + "args": { + "External id": 1426890,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850165704.714, "dur": 12.839, + "args": { + "External id": 1426891,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850165709.751, "dur": 7.304, + "args": { + "External id": 1426892,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165714.960, "dur": 0.745, + "args": { + "External id": 1426893,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850165725.060, "dur": 34.478, + "args": { + "External id": 1426894,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165727.701, "dur": 0.500, + "args": { + "External id": 1426895,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165730.263, "dur": 2.292, + "args": { + "External id": 1426896,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165734.607, "dur": 0.574, + "args": { + "External id": 1426897,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165736.535, "dur": 2.781, + "args": { + "External id": 1426898,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165742.955, "dur": 0.392, + "args": { + "External id": 1426899,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165744.965, "dur": 0.586, + "args": { + "External id": 1426900,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165747.651, "dur": 0.597, + "args": { + "External id": 1426901,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165751.938, "dur": 0.457, + "args": { + "External id": 1426902,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850165753.808, "dur": 0.607, + "args": { + "External id": 1426903,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850165771.440, "dur": 37.100, + "args": { + "External id": 1426904,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850165879.933, "dur": 510.394, + "args": { + "External id": 1426905,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850165917.606, "dur": 466.374, + "args": { + "External id": 1426906,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13342, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850165928.989, "dur": 445.831, + "args": { + "External id": 1426907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850166421.891, "dur": 3.030, + "args": { + "External id": 1426908,"Record function id": 0, "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": 13344, "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": 2338706, "tid": 2338706, + "ts": 6413850166533.581, "dur": 32632.145, + "args": { + "External id": 1426909,"Record function id": 0, "Ev Idx": 13345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166655.094, "dur": 7.648, + "args": { + "External id": 1426910,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166667.113, "dur": 0.983, + "args": { + "External id": 1426911,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166670.056, "dur": 3.644, + "args": { + "External id": 1426912,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166676.017, "dur": 0.948, + "args": { + "External id": 1426913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166679.003, "dur": 1.144, + "args": { + "External id": 1426914,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166681.998, "dur": 0.858, + "args": { + "External id": 1426915,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166684.922, "dur": 0.927, + "args": { + "External id": 1426916,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166687.910, "dur": 2.492, + "args": { + "External id": 1426917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166692.414, "dur": 1.004, + "args": { + "External id": 1426918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850166697.376, "dur": 0.975, + "args": { + "External id": 1426919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850166718.711, "dur": 32378.678, + "args": { + "External id": 1426920,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850166736.762, "dur": 32348.851, + "args": { + "External id": 1426921,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850166759.148, "dur": 19.388, + "args": { + "External id": 1426922,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850166782.589, "dur": 32219.421, + "args": { + "External id": 1426923,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850166785.658, "dur": 32215.429, + "args": { + "External id": 1426924,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850166792.361, "dur": 6.055, + "args": { + "External id": 1426925,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850166800.501, "dur": 32195.279, + "args": { + "External id": 1426926,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850199362.738, "dur": 42.111, + "args": { + "External id": 1426927,"Sequence number": 15348691, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13363 + } + }, + { + "ph": "s", "id": 191, "pid": 2338706, "tid": 2338706, "ts": 6413850199362.738, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850199384.157, "dur": 15.163, + "args": { + "External id": 1426928,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850199390.347, "dur": 8.020, + "args": { + "External id": 1426929,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850199495.706, "dur": 87.859, + "args": { + "External id": 1426930,"Record function id": 0, "Ev Idx": 13366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850199585.659, "dur": 1531.414, + "args": { + "External id": 1426931,"Record function id": 0, "Ev Idx": 13367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850199633.337, "dur": 1463.431, + "args": { + "External id": 1426932,"Sequence number": 15348692, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13368 + } + }, + { + "ph": "s", "id": 190, "pid": 2338706, "tid": 2338706, "ts": 6413850199633.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850199725.704, "dur": 61.163, + "args": { + "External id": 1426933,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850199803.198, "dur": 118.154, + "args": { + "External id": 1426934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850199936.233, "dur": 66.497, + "args": { + "External id": 1426935,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850200018.151, "dur": 82.195, + "args": { + "External id": 1426936,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850200151.543, "dur": 40.087, + "args": { + "External id": 1426937,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850200217.901, "dur": 22.329, + "args": { + "External id": 1426938,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850200269.339, "dur": 159.252, + "args": { + "External id": 1426939,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850200325.896, "dur": 15.832, + "args": { + "External id": 1426940,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850200333.068, "dur": 7.510, + "args": { + "External id": 1426941,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850200346.390, "dur": 5.571, + "args": { + "External id": 1426942,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850200353.480, "dur": 1.571, + "args": { + "External id": 1426943,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850200358.052, "dur": 7.703, + "args": { + "External id": 1426944,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850200512.455, "dur": 84.650, + "args": { + "External id": 1426945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850200642.506, "dur": 40.065, + "args": { + "External id": 1426946,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850200694.741, "dur": 53.027, + "args": { + "External id": 1426947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850200758.107, "dur": 41.713, + "args": { + "External id": 1426948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850200826.665, "dur": 31.971, + "args": { + "External id": 1426949,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850200865.409, "dur": 43.227, + "args": { + "External id": 1426950,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850200933.564, "dur": 22.728, + "args": { + "External id": 1426951,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 2338706, "tid": 2338706, + "ts": 6413850201199.365, "dur": 97.567, + "args": { + "External id": 1426952,"Record function id": 0, "Ev Idx": 13388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850201390.046, "dur": 55.794, + "args": { + "External id": 1426953,"Record function id": 0, "Ev Idx": 13389 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338706, "tid": 2338706, + "ts": 6413850201456.798, "dur": 32506.514, + "args": { + "External id": 1426954,"Record function id": 0, "Ev Idx": 13390 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338706, "tid": 2338706, + "ts": 6413850201466.655, "dur": 1037.472, + "args": { + "External id": 1426955,"Record function id": 0, "Ev Idx": 13391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850201562.895, "dur": 11.725, + "args": { + "External id": 1426956,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850201590.722, "dur": 45.446, + "args": { + "External id": 1426957,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201597.433, "dur": 2.552, + "args": { + "External id": 1426958,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201605.627, "dur": 0.481, + "args": { + "External id": 1426959,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201608.124, "dur": 1.038, + "args": { + "External id": 1426960,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201611.299, "dur": 0.691, + "args": { + "External id": 1426961,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201615.102, "dur": 0.566, + "args": { + "External id": 1426962,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201617.198, "dur": 0.693, + "args": { + "External id": 1426963,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201620.296, "dur": 4.329, + "args": { + "External id": 1426964,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201626.356, "dur": 0.641, + "args": { + "External id": 1426965,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201628.482, "dur": 0.511, + "args": { + "External id": 1426966,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850201649.888, "dur": 66.514, + "args": { + "External id": 1426967,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850201758.378, "dur": 144.591, + "args": { + "External id": 1426968,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850201772.506, "dur": 5.260, + "args": { + "External id": 1426969,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850201783.858, "dur": 11.864, + "args": { + "External id": 1426970,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850201788.954, "dur": 6.279, + "args": { + "External id": 1426971,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201792.987, "dur": 0.915, + "args": { + "External id": 1426972,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850201803.303, "dur": 36.595, + "args": { + "External id": 1426973,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201805.860, "dur": 2.935, + "args": { + "External id": 1426974,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201810.527, "dur": 0.601, + "args": { + "External id": 1426975,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201813.416, "dur": 0.613, + "args": { + "External id": 1426976,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201817.619, "dur": 3.015, + "args": { + "External id": 1426977,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201822.392, "dur": 0.534, + "args": { + "External id": 1426978,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201824.418, "dur": 0.492, + "args": { + "External id": 1426979,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201827.818, "dur": 0.454, + "args": { + "External id": 1426980,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201829.737, "dur": 0.782, + "args": { + "External id": 1426981,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850201831.968, "dur": 2.713, + "args": { + "External id": 1426982,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850201855.099, "dur": 38.049, + "args": { + "External id": 1426983,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850201965.344, "dur": 423.751, + "args": { + "External id": 1426984,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850202024.787, "dur": 358.300, + "args": { + "External id": 1426985,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13421, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850202036.896, "dur": 339.512, + "args": { + "External id": 1426986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850202417.753, "dur": 3.165, + "args": { + "External id": 1426987,"Record function id": 0, "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": 13423, "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": 2338706, "tid": 2338706, + "ts": 6413850202527.709, "dur": 31161.744, + "args": { + "External id": 1426988,"Record function id": 0, "Ev Idx": 13424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202648.216, "dur": 7.193, + "args": { + "External id": 1426989,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202659.677, "dur": 1.384, + "args": { + "External id": 1426990,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202663.219, "dur": 3.398, + "args": { + "External id": 1426991,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202668.740, "dur": 1.124, + "args": { + "External id": 1426992,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202671.522, "dur": 1.135, + "args": { + "External id": 1426993,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202674.309, "dur": 1.097, + "args": { + "External id": 1426994,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202679.423, "dur": 1.101, + "args": { + "External id": 1426995,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202682.283, "dur": 2.705, + "args": { + "External id": 1426996,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202686.655, "dur": 0.841, + "args": { + "External id": 1426997,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850202689.163, "dur": 1.045, + "args": { + "External id": 1426998,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850202712.780, "dur": 30911.018, + "args": { + "External id": 1426999,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850202731.304, "dur": 30881.583, + "args": { + "External id": 1427000,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850202754.444, "dur": 19.995, + "args": { + "External id": 1427001,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850202778.566, "dur": 30784.449, + "args": { + "External id": 1427002,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850202781.536, "dur": 30779.965, + "args": { + "External id": 1427003,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850202788.089, "dur": 6.182, + "args": { + "External id": 1427004,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850202795.857, "dur": 30761.215, + "args": { + "External id": 1427005,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850233885.126, "dur": 41.182, + "args": { + "External id": 1427006,"Sequence number": 15348693, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13442 + } + }, + { + "ph": "s", "id": 189, "pid": 2338706, "tid": 2338706, "ts": 6413850233885.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850233906.583, "dur": 13.131, + "args": { + "External id": 1427007,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850233912.528, "dur": 6.944, + "args": { + "External id": 1427008,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850234040.377, "dur": 120.873, + "args": { + "External id": 1427009,"Record function id": 0, "Ev Idx": 13445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850234164.757, "dur": 1350.871, + "args": { + "External id": 1427010,"Record function id": 0, "Ev Idx": 13446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850234215.295, "dur": 1283.250, + "args": { + "External id": 1427011,"Sequence number": 15348694, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13447 + } + }, + { + "ph": "s", "id": 188, "pid": 2338706, "tid": 2338706, "ts": 6413850234215.295, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850234303.452, "dur": 63.782, + "args": { + "External id": 1427012,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850234383.910, "dur": 119.377, + "args": { + "External id": 1427013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850234518.956, "dur": 44.074, + "args": { + "External id": 1427014,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850234573.651, "dur": 34.165, + "args": { + "External id": 1427015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850234640.839, "dur": 31.695, + "args": { + "External id": 1427016,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850234696.207, "dur": 22.904, + "args": { + "External id": 1427017,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850234745.767, "dur": 158.170, + "args": { + "External id": 1427018,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850234802.944, "dur": 16.735, + "args": { + "External id": 1427019,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850234810.665, "dur": 7.939, + "args": { + "External id": 1427020,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850234823.808, "dur": 5.104, + "args": { + "External id": 1427021,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850234830.740, "dur": 1.189, + "args": { + "External id": 1427022,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850234834.975, "dur": 6.315, + "args": { + "External id": 1427023,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850234918.102, "dur": 76.211, + "args": { + "External id": 1427024,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850235040.136, "dur": 80.218, + "args": { + "External id": 1427025,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850235136.960, "dur": 60.365, + "args": { + "External id": 1427026,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850235208.576, "dur": 41.917, + "args": { + "External id": 1427027,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850235280.481, "dur": 36.873, + "args": { + "External id": 1427028,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850235326.429, "dur": 42.542, + "args": { + "External id": 1427029,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850235389.782, "dur": 20.761, + "args": { + "External id": 1427030,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13466 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 2338706, "tid": 2338706, + "ts": 6413850235591.967, "dur": 94.580, + "args": { + "External id": 1427031,"Record function id": 0, "Ev Idx": 13467 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850235776.565, "dur": 57.953, + "args": { + "External id": 1427032,"Record function id": 0, "Ev Idx": 13468 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338706, "tid": 2338706, + "ts": 6413850235845.207, "dur": 33110.772, + "args": { + "External id": 1427033,"Record function id": 0, "Ev Idx": 13469 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338706, "tid": 2338706, + "ts": 6413850235854.893, "dur": 1086.997, + "args": { + "External id": 1427034,"Record function id": 0, "Ev Idx": 13470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850235951.808, "dur": 10.439, + "args": { + "External id": 1427035,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850235998.395, "dur": 44.884, + "args": { + "External id": 1427036,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236005.660, "dur": 2.803, + "args": { + "External id": 1427037,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236013.158, "dur": 0.937, + "args": { + "External id": 1427038,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236015.475, "dur": 0.361, + "args": { + "External id": 1427039,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236017.896, "dur": 0.791, + "args": { + "External id": 1427040,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236022.983, "dur": 0.483, + "args": { + "External id": 1427041,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236025.186, "dur": 0.691, + "args": { + "External id": 1427042,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236026.921, "dur": 4.180, + "args": { + "External id": 1427043,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236032.470, "dur": 0.611, + "args": { + "External id": 1427044,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236034.308, "dur": 0.504, + "args": { + "External id": 1427045,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850236097.135, "dur": 67.277, + "args": { + "External id": 1427046,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850236208.431, "dur": 149.675, + "args": { + "External id": 1427047,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850236226.437, "dur": 8.796, + "args": { + "External id": 1427048,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850236241.874, "dur": 12.418, + "args": { + "External id": 1427049,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850236246.936, "dur": 6.626, + "args": { + "External id": 1427050,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236251.011, "dur": 0.706, + "args": { + "External id": 1427051,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850236262.867, "dur": 31.129, + "args": { + "External id": 1427052,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236265.174, "dur": 0.689, + "args": { + "External id": 1427053,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236267.712, "dur": 2.304, + "args": { + "External id": 1427054,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236271.569, "dur": 0.454, + "args": { + "External id": 1427055,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236273.581, "dur": 2.905, + "args": { + "External id": 1427056,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236279.974, "dur": 0.373, + "args": { + "External id": 1427057,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236281.863, "dur": 0.500, + "args": { + "External id": 1427058,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236283.491, "dur": 0.305, + "args": { + "External id": 1427059,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236286.657, "dur": 0.346, + "args": { + "External id": 1427060,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850236288.434, "dur": 0.472, + "args": { + "External id": 1427061,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850236306.931, "dur": 40.938, + "args": { + "External id": 1427062,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850236423.784, "dur": 409.429, + "args": { + "External id": 1427063,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850236461.453, "dur": 366.243, + "args": { + "External id": 1427064,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13500, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850236473.179, "dur": 348.245, + "args": { + "External id": 1427065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850236860.286, "dur": 2.666, + "args": { + "External id": 1427066,"Record function id": 0, "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": 13502, "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": 2338706, "tid": 2338706, + "ts": 6413850236967.042, "dur": 31722.229, + "args": { + "External id": 1427067,"Record function id": 0, "Ev Idx": 13503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237160.500, "dur": 7.673, + "args": { + "External id": 1427068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237172.913, "dur": 1.402, + "args": { + "External id": 1427069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237176.612, "dur": 3.130, + "args": { + "External id": 1427070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237182.058, "dur": 0.981, + "args": { + "External id": 1427071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237185.094, "dur": 0.728, + "args": { + "External id": 1427072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237187.477, "dur": 0.916, + "args": { + "External id": 1427073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237190.361, "dur": 1.129, + "args": { + "External id": 1427074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237193.674, "dur": 2.726, + "args": { + "External id": 1427075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237198.118, "dur": 0.940, + "args": { + "External id": 1427076,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850237203.353, "dur": 0.941, + "args": { + "External id": 1427077,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850237226.563, "dur": 31403.415, + "args": { + "External id": 1427078,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850237245.406, "dur": 31373.265, + "args": { + "External id": 1427079,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850237265.153, "dur": 19.811, + "args": { + "External id": 1427080,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850237289.233, "dur": 31279.252, + "args": { + "External id": 1427081,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850237292.018, "dur": 31275.438, + "args": { + "External id": 1427082,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850237298.268, "dur": 6.172, + "args": { + "External id": 1427083,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850237306.736, "dur": 31255.927, + "args": { + "External id": 1427084,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850268881.501, "dur": 39.866, + "args": { + "External id": 1427085,"Sequence number": 15348695, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13521 + } + }, + { + "ph": "s", "id": 187, "pid": 2338706, "tid": 2338706, "ts": 6413850268881.501, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850268901.546, "dur": 12.759, + "args": { + "External id": 1427086,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850268907.113, "dur": 6.911, + "args": { + "External id": 1427087,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850269026.796, "dur": 120.612, + "args": { + "External id": 1427088,"Record function id": 0, "Ev Idx": 13524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850269150.740, "dur": 1355.474, + "args": { + "External id": 1427089,"Record function id": 0, "Ev Idx": 13525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850269199.429, "dur": 1289.031, + "args": { + "External id": 1427090,"Sequence number": 15348696, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13526 + } + }, + { + "ph": "s", "id": 186, "pid": 2338706, "tid": 2338706, "ts": 6413850269199.429, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850269297.840, "dur": 63.317, + "args": { + "External id": 1427091,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850269384.492, "dur": 121.195, + "args": { + "External id": 1427092,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850269521.703, "dur": 44.377, + "args": { + "External id": 1427093,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850269573.662, "dur": 34.208, + "args": { + "External id": 1427094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850269642.944, "dur": 34.506, + "args": { + "External id": 1427095,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850269701.044, "dur": 24.424, + "args": { + "External id": 1427096,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850269750.829, "dur": 162.303, + "args": { + "External id": 1427097,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850269810.612, "dur": 16.256, + "args": { + "External id": 1427098,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850269817.685, "dur": 8.099, + "args": { + "External id": 1427099,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850269831.139, "dur": 5.138, + "args": { + "External id": 1427100,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850269837.573, "dur": 2.795, + "args": { + "External id": 1427101,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850269843.162, "dur": 5.617, + "args": { + "External id": 1427102,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850269926.363, "dur": 78.608, + "args": { + "External id": 1427103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850270049.075, "dur": 79.871, + "args": { + "External id": 1427104,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850270146.783, "dur": 60.212, + "args": { + "External id": 1427105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850270216.492, "dur": 41.894, + "args": { + "External id": 1427106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850270285.810, "dur": 32.757, + "args": { + "External id": 1427107,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850270324.736, "dur": 41.894, + "args": { + "External id": 1427108,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850270388.952, "dur": 23.948, + "args": { + "External id": 1427109,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13545 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 2338706, "tid": 2338706, + "ts": 6413850270580.235, "dur": 87.911, + "args": { + "External id": 1427110,"Record function id": 0, "Ev Idx": 13546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850270759.248, "dur": 56.589, + "args": { + "External id": 1427111,"Record function id": 0, "Ev Idx": 13547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338706, "tid": 2338706, + "ts": 6413850270826.709, "dur": 29645.457, + "args": { + "External id": 1427112,"Record function id": 0, "Ev Idx": 13548 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338706, "tid": 2338706, + "ts": 6413850270836.552, "dur": 1082.504, + "args": { + "External id": 1427113,"Record function id": 0, "Ev Idx": 13549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850270933.574, "dur": 10.329, + "args": { + "External id": 1427114,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850270959.832, "dur": 61.429, + "args": { + "External id": 1427115,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850270965.755, "dur": 2.389, + "args": { + "External id": 1427116,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850270971.977, "dur": 0.435, + "args": { + "External id": 1427117,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850270994.135, "dur": 1.017, + "args": { + "External id": 1427118,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850270998.704, "dur": 0.426, + "args": { + "External id": 1427119,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271001.535, "dur": 0.517, + "args": { + "External id": 1427120,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271003.949, "dur": 0.393, + "args": { + "External id": 1427121,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271006.125, "dur": 3.801, + "args": { + "External id": 1427122,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271011.608, "dur": 0.480, + "args": { + "External id": 1427123,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271013.382, "dur": 0.594, + "args": { + "External id": 1427124,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850271035.380, "dur": 109.500, + "args": { + "External id": 1427125,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850271191.278, "dur": 145.966, + "args": { + "External id": 1427126,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850271206.739, "dur": 6.710, + "args": { + "External id": 1427127,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850271219.974, "dur": 12.293, + "args": { + "External id": 1427128,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850271224.884, "dur": 6.910, + "args": { + "External id": 1427129,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271229.091, "dur": 0.975, + "args": { + "External id": 1427130,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850271239.706, "dur": 31.155, + "args": { + "External id": 1427131,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271242.388, "dur": 2.125, + "args": { + "External id": 1427132,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271245.979, "dur": 0.439, + "args": { + "External id": 1427133,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271247.641, "dur": 0.385, + "args": { + "External id": 1427134,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271251.312, "dur": 2.637, + "args": { + "External id": 1427135,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271255.635, "dur": 0.286, + "args": { + "External id": 1427136,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271257.768, "dur": 0.440, + "args": { + "External id": 1427137,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271261.416, "dur": 0.340, + "args": { + "External id": 1427138,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271262.808, "dur": 0.407, + "args": { + "External id": 1427139,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850271264.836, "dur": 1.489, + "args": { + "External id": 1427140,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850271286.494, "dur": 40.843, + "args": { + "External id": 1427141,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850271403.042, "dur": 411.309, + "args": { + "External id": 1427142,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850271439.789, "dur": 368.608, + "args": { + "External id": 1427143,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13579, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850271451.208, "dur": 350.870, + "args": { + "External id": 1427144,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850271839.851, "dur": 2.690, + "args": { + "External id": 1427145,"Record function id": 0, "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": 13581, "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": 2338706, "tid": 2338706, + "ts": 6413850271942.814, "dur": 28277.063, + "args": { + "External id": 1427146,"Record function id": 0, "Ev Idx": 13582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272131.827, "dur": 7.964, + "args": { + "External id": 1427147,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272158.163, "dur": 1.262, + "args": { + "External id": 1427148,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272162.782, "dur": 3.879, + "args": { + "External id": 1427149,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272170.571, "dur": 1.416, + "args": { + "External id": 1427150,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272173.665, "dur": 1.535, + "args": { + "External id": 1427151,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272176.874, "dur": 1.103, + "args": { + "External id": 1427152,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272179.979, "dur": 1.004, + "args": { + "External id": 1427153,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272185.374, "dur": 2.127, + "args": { + "External id": 1427154,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272189.113, "dur": 0.768, + "args": { + "External id": 1427155,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850272191.602, "dur": 0.758, + "args": { + "External id": 1427156,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850272214.707, "dur": 27942.408, + "args": { + "External id": 1427157,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850272233.970, "dur": 27911.202, + "args": { + "External id": 1427158,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850272251.170, "dur": 19.873, + "args": { + "External id": 1427159,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850272277.766, "dur": 27818.043, + "args": { + "External id": 1427160,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850272280.825, "dur": 27814.179, + "args": { + "External id": 1427161,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850272286.456, "dur": 6.324, + "args": { + "External id": 1427162,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850272294.697, "dur": 27794.919, + "args": { + "External id": 1427163,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850300402.184, "dur": 40.842, + "args": { + "External id": 1427164,"Sequence number": 15348697, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13600 + } + }, + { + "ph": "s", "id": 185, "pid": 2338706, "tid": 2338706, "ts": 6413850300402.184, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850300423.871, "dur": 13.425, + "args": { + "External id": 1427165,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850300429.850, "dur": 7.204, + "args": { + "External id": 1427166,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850300522.802, "dur": 92.685, + "args": { + "External id": 1427167,"Record function id": 0, "Ev Idx": 13603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850300617.370, "dur": 1326.096, + "args": { + "External id": 1427168,"Record function id": 0, "Ev Idx": 13604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850300662.240, "dur": 1264.839, + "args": { + "External id": 1427169,"Sequence number": 15348698, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13605 + } + }, + { + "ph": "s", "id": 184, "pid": 2338706, "tid": 2338706, "ts": 6413850300662.240, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850300749.400, "dur": 57.356, + "args": { + "External id": 1427170,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850300822.311, "dur": 120.305, + "args": { + "External id": 1427171,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850300958.777, "dur": 66.936, + "args": { + "External id": 1427172,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850301039.860, "dur": 79.750, + "args": { + "External id": 1427173,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850301161.255, "dur": 38.273, + "args": { + "External id": 1427174,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850301224.751, "dur": 23.268, + "args": { + "External id": 1427175,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850301274.295, "dur": 154.661, + "args": { + "External id": 1427176,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850301333.048, "dur": 14.805, + "args": { + "External id": 1427177,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850301340.367, "dur": 6.404, + "args": { + "External id": 1427178,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850301350.656, "dur": 4.947, + "args": { + "External id": 1427179,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850301356.952, "dur": 1.479, + "args": { + "External id": 1427180,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850301361.163, "dur": 5.824, + "args": { + "External id": 1427181,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850301442.030, "dur": 64.047, + "args": { + "External id": 1427182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850301542.955, "dur": 36.609, + "args": { + "External id": 1427183,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850301591.625, "dur": 51.845, + "args": { + "External id": 1427184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850301653.963, "dur": 41.136, + "args": { + "External id": 1427185,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850301720.476, "dur": 32.777, + "args": { + "External id": 1427186,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850301760.513, "dur": 41.295, + "args": { + "External id": 1427187,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850301823.428, "dur": 19.482, + "args": { + "External id": 1427188,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13624 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 2338706, "tid": 2338706, + "ts": 6413850302046.449, "dur": 137.084, + "args": { + "External id": 1427189,"Record function id": 0, "Ev Idx": 13625 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850302284.804, "dur": 57.780, + "args": { + "External id": 1427190,"Record function id": 0, "Ev Idx": 13626 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338706, "tid": 2338706, + "ts": 6413850302352.931, "dur": 29078.963, + "args": { + "External id": 1427191,"Record function id": 0, "Ev Idx": 13627 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338706, "tid": 2338706, + "ts": 6413850302364.659, "dur": 1129.179, + "args": { + "External id": 1427192,"Record function id": 0, "Ev Idx": 13628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850302461.149, "dur": 10.557, + "args": { + "External id": 1427193,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850302486.613, "dur": 37.931, + "args": { + "External id": 1427194,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302492.866, "dur": 2.661, + "args": { + "External id": 1427195,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302499.673, "dur": 0.804, + "args": { + "External id": 1427196,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302502.171, "dur": 0.468, + "args": { + "External id": 1427197,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302503.893, "dur": 0.687, + "args": { + "External id": 1427198,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302506.968, "dur": 0.637, + "args": { + "External id": 1427199,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302508.653, "dur": 0.455, + "args": { + "External id": 1427200,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302510.392, "dur": 4.249, + "args": { + "External id": 1427201,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302515.744, "dur": 0.425, + "args": { + "External id": 1427202,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302517.275, "dur": 0.507, + "args": { + "External id": 1427203,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850302537.485, "dur": 65.419, + "args": { + "External id": 1427204,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850302641.523, "dur": 132.132, + "args": { + "External id": 1427205,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850302653.223, "dur": 5.460, + "args": { + "External id": 1427206,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850302664.907, "dur": 11.687, + "args": { + "External id": 1427207,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850302670.137, "dur": 5.973, + "args": { + "External id": 1427208,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302673.943, "dur": 0.686, + "args": { + "External id": 1427209,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850302684.123, "dur": 30.711, + "args": { + "External id": 1427210,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302686.014, "dur": 2.108, + "args": { + "External id": 1427211,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302689.904, "dur": 0.578, + "args": { + "External id": 1427212,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302694.965, "dur": 0.566, + "args": { + "External id": 1427213,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302698.408, "dur": 2.680, + "args": { + "External id": 1427214,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302702.296, "dur": 0.470, + "args": { + "External id": 1427215,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302703.933, "dur": 0.456, + "args": { + "External id": 1427216,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302705.575, "dur": 0.273, + "args": { + "External id": 1427217,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302706.865, "dur": 0.632, + "args": { + "External id": 1427218,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850302710.010, "dur": 0.317, + "args": { + "External id": 1427219,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850302728.551, "dur": 35.423, + "args": { + "External id": 1427220,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850302838.002, "dur": 531.740, + "args": { + "External id": 1427221,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850302874.074, "dur": 488.960, + "args": { + "External id": 1427222,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13658, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850302885.141, "dur": 469.959, + "args": { + "External id": 1427223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850303403.323, "dur": 2.942, + "args": { + "External id": 1427224,"Record function id": 0, "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": 13660, "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": 2338706, "tid": 2338706, + "ts": 6413850303518.458, "dur": 27666.086, + "args": { + "External id": 1427225,"Record function id": 0, "Ev Idx": 13661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303637.000, "dur": 7.217, + "args": { + "External id": 1427226,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303648.451, "dur": 1.294, + "args": { + "External id": 1427227,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303652.396, "dur": 3.989, + "args": { + "External id": 1427228,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303658.566, "dur": 1.024, + "args": { + "External id": 1427229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303661.804, "dur": 1.227, + "args": { + "External id": 1427230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303665.210, "dur": 0.802, + "args": { + "External id": 1427231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303668.021, "dur": 1.065, + "args": { + "External id": 1427232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303671.344, "dur": 2.551, + "args": { + "External id": 1427233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303675.818, "dur": 0.977, + "args": { + "External id": 1427234,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850303680.897, "dur": 0.883, + "args": { + "External id": 1427235,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850303701.863, "dur": 27425.040, + "args": { + "External id": 1427236,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850303720.928, "dur": 27394.719, + "args": { + "External id": 1427237,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850303740.924, "dur": 19.084, + "args": { + "External id": 1427238,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850303764.054, "dur": 27277.344, + "args": { + "External id": 1427239,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850303767.437, "dur": 27273.251, + "args": { + "External id": 1427240,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850303772.721, "dur": 7.064, + "args": { + "External id": 1427241,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850303782.104, "dur": 27253.519, + "args": { + "External id": 1427242,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850331357.878, "dur": 43.745, + "args": { + "External id": 1427243,"Sequence number": 15348699, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13679 + } + }, + { + "ph": "s", "id": 183, "pid": 2338706, "tid": 2338706, "ts": 6413850331357.878, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850331384.165, "dur": 11.331, + "args": { + "External id": 1427244,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850331389.104, "dur": 6.064, + "args": { + "External id": 1427245,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850331478.804, "dur": 82.227, + "args": { + "External id": 1427246,"Record function id": 0, "Ev Idx": 13682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850331562.471, "dur": 1302.563, + "args": { + "External id": 1427247,"Record function id": 0, "Ev Idx": 13683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850331607.361, "dur": 1240.625, + "args": { + "External id": 1427248,"Sequence number": 15348700, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13684 + } + }, + { + "ph": "s", "id": 182, "pid": 2338706, "tid": 2338706, "ts": 6413850331607.361, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850331693.676, "dur": 57.693, + "args": { + "External id": 1427249,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850331767.009, "dur": 114.459, + "args": { + "External id": 1427250,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850331897.641, "dur": 43.358, + "args": { + "External id": 1427251,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850331949.788, "dur": 55.927, + "args": { + "External id": 1427252,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850332043.556, "dur": 80.732, + "args": { + "External id": 1427253,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850332154.461, "dur": 22.632, + "args": { + "External id": 1427254,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850332202.614, "dur": 157.885, + "args": { + "External id": 1427255,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850332262.454, "dur": 15.005, + "args": { + "External id": 1427256,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850332269.851, "dur": 6.640, + "args": { + "External id": 1427257,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850332280.910, "dur": 4.778, + "args": { + "External id": 1427258,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850332287.319, "dur": 1.566, + "args": { + "External id": 1427259,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850332293.755, "dur": 5.990, + "args": { + "External id": 1427260,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850332373.110, "dur": 65.138, + "args": { + "External id": 1427261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850332474.427, "dur": 35.429, + "args": { + "External id": 1427262,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850332521.973, "dur": 48.081, + "args": { + "External id": 1427263,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850332579.700, "dur": 40.756, + "args": { + "External id": 1427264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850332645.535, "dur": 33.499, + "args": { + "External id": 1427265,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850332685.279, "dur": 41.520, + "args": { + "External id": 1427266,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850332749.421, "dur": 22.385, + "args": { + "External id": 1427267,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13703 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 2338706, "tid": 2338706, + "ts": 6413850332937.011, "dur": 151.055, + "args": { + "External id": 1427268,"Record function id": 0, "Ev Idx": 13704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850333189.514, "dur": 58.112, + "args": { + "External id": 1427269,"Record function id": 0, "Ev Idx": 13705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338706, "tid": 2338706, + "ts": 6413850333258.377, "dur": 29096.236, + "args": { + "External id": 1427270,"Record function id": 0, "Ev Idx": 13706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338706, "tid": 2338706, + "ts": 6413850333268.407, "dur": 1108.989, + "args": { + "External id": 1427271,"Record function id": 0, "Ev Idx": 13707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850333369.445, "dur": 14.256, + "args": { + "External id": 1427272,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850333399.233, "dur": 42.888, + "args": { + "External id": 1427273,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333406.241, "dur": 2.598, + "args": { + "External id": 1427274,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333413.627, "dur": 0.613, + "args": { + "External id": 1427275,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333416.144, "dur": 0.664, + "args": { + "External id": 1427276,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333418.533, "dur": 0.468, + "args": { + "External id": 1427277,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333421.744, "dur": 0.609, + "args": { + "External id": 1427278,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333424.301, "dur": 0.397, + "args": { + "External id": 1427279,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333426.281, "dur": 3.554, + "args": { + "External id": 1427280,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333431.837, "dur": 0.564, + "args": { + "External id": 1427281,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333434.063, "dur": 0.611, + "args": { + "External id": 1427282,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850333455.725, "dur": 61.670, + "args": { + "External id": 1427283,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850333553.454, "dur": 138.251, + "args": { + "External id": 1427284,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850333565.829, "dur": 4.868, + "args": { + "External id": 1427285,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850333576.425, "dur": 12.191, + "args": { + "External id": 1427286,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850333581.491, "dur": 6.649, + "args": { + "External id": 1427287,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333586.130, "dur": 0.735, + "args": { + "External id": 1427288,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850333595.827, "dur": 32.714, + "args": { + "External id": 1427289,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333598.526, "dur": 1.623, + "args": { + "External id": 1427290,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333602.023, "dur": 0.613, + "args": { + "External id": 1427291,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333604.325, "dur": 0.357, + "args": { + "External id": 1427292,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333607.830, "dur": 2.700, + "args": { + "External id": 1427293,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333612.428, "dur": 0.350, + "args": { + "External id": 1427294,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333614.536, "dur": 0.392, + "args": { + "External id": 1427295,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333618.155, "dur": 0.570, + "args": { + "External id": 1427296,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333620.303, "dur": 0.277, + "args": { + "External id": 1427297,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850333622.216, "dur": 1.613, + "args": { + "External id": 1427298,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850333642.567, "dur": 39.289, + "args": { + "External id": 1427299,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850333764.690, "dur": 489.182, + "args": { + "External id": 1427300,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850333802.390, "dur": 445.027, + "args": { + "External id": 1427301,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13737, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850333817.335, "dur": 421.915, + "args": { + "External id": 1427302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850334286.013, "dur": 2.653, + "args": { + "External id": 1427303,"Record function id": 0, "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": 13739, "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": 2338706, "tid": 2338706, + "ts": 6413850334402.035, "dur": 27702.175, + "args": { + "External id": 1427304,"Record function id": 0, "Ev Idx": 13740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334524.164, "dur": 7.427, + "args": { + "External id": 1427305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334535.604, "dur": 1.202, + "args": { + "External id": 1427306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334539.060, "dur": 3.431, + "args": { + "External id": 1427307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334544.704, "dur": 1.056, + "args": { + "External id": 1427308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334547.429, "dur": 1.192, + "args": { + "External id": 1427309,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334550.108, "dur": 1.187, + "args": { + "External id": 1427310,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334553.243, "dur": 0.820, + "args": { + "External id": 1427311,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334556.069, "dur": 2.134, + "args": { + "External id": 1427312,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334559.946, "dur": 0.980, + "args": { + "External id": 1427313,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850334564.965, "dur": 0.809, + "args": { + "External id": 1427314,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850334586.171, "dur": 27422.625, + "args": { + "External id": 1427315,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850334606.365, "dur": 27390.495, + "args": { + "External id": 1427316,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850334626.462, "dur": 18.937, + "args": { + "External id": 1427317,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850334649.418, "dur": 27284.376, + "args": { + "External id": 1427318,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850334652.416, "dur": 27280.588, + "args": { + "External id": 1427319,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850334658.888, "dur": 6.154, + "args": { + "External id": 1427320,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850334666.806, "dur": 27260.829, + "args": { + "External id": 1427321,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850362284.913, "dur": 40.030, + "args": { + "External id": 1427322,"Sequence number": 15348701, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13758 + } + }, + { + "ph": "s", "id": 181, "pid": 2338706, "tid": 2338706, "ts": 6413850362284.913, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850362305.692, "dur": 13.327, + "args": { + "External id": 1427323,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850362311.596, "dur": 7.169, + "args": { + "External id": 1427324,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850362403.914, "dur": 81.925, + "args": { + "External id": 1427325,"Record function id": 0, "Ev Idx": 13761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850362488.144, "dur": 1328.055, + "args": { + "External id": 1427326,"Record function id": 0, "Ev Idx": 13762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850362531.372, "dur": 1268.064, + "args": { + "External id": 1427327,"Sequence number": 15348702, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13763 + } + }, + { + "ph": "s", "id": 180, "pid": 2338706, "tid": 2338706, "ts": 6413850362531.372, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850362618.548, "dur": 58.460, + "args": { + "External id": 1427328,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850362693.141, "dur": 120.155, + "args": { + "External id": 1427329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850362829.163, "dur": 42.401, + "args": { + "External id": 1427330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850362881.099, "dur": 34.954, + "args": { + "External id": 1427331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850362945.924, "dur": 52.995, + "args": { + "External id": 1427332,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850363032.907, "dur": 67.988, + "args": { + "External id": 1427333,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850363133.304, "dur": 164.277, + "args": { + "External id": 1427334,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850363193.727, "dur": 15.291, + "args": { + "External id": 1427335,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850363200.919, "dur": 7.136, + "args": { + "External id": 1427336,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850363212.468, "dur": 4.976, + "args": { + "External id": 1427337,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850363222.289, "dur": 1.772, + "args": { + "External id": 1427338,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850363226.785, "dur": 5.946, + "args": { + "External id": 1427339,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850363311.316, "dur": 66.559, + "args": { + "External id": 1427340,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850363416.049, "dur": 38.653, + "args": { + "External id": 1427341,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850363465.953, "dur": 51.730, + "args": { + "External id": 1427342,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850363528.423, "dur": 40.394, + "args": { + "External id": 1427343,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850363593.534, "dur": 30.882, + "args": { + "External id": 1427344,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850363632.170, "dur": 40.807, + "args": { + "External id": 1427345,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850363695.577, "dur": 23.482, + "args": { + "External id": 1427346,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13782 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 2338706, "tid": 2338706, + "ts": 6413850363891.373, "dur": 116.038, + "args": { + "External id": 1427347,"Record function id": 0, "Ev Idx": 13783 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850364145.302, "dur": 58.028, + "args": { + "External id": 1427348,"Record function id": 0, "Ev Idx": 13784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338706, "tid": 2338706, + "ts": 6413850364215.095, "dur": 30235.376, + "args": { + "External id": 1427349,"Record function id": 0, "Ev Idx": 13785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338706, "tid": 2338706, + "ts": 6413850364226.033, "dur": 1087.731, + "args": { + "External id": 1427350,"Record function id": 0, "Ev Idx": 13786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850364321.833, "dur": 12.228, + "args": { + "External id": 1427351,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850364349.563, "dur": 41.367, + "args": { + "External id": 1427352,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364356.409, "dur": 2.590, + "args": { + "External id": 1427353,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364363.561, "dur": 0.457, + "args": { + "External id": 1427354,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364366.088, "dur": 0.335, + "args": { + "External id": 1427355,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364368.301, "dur": 0.503, + "args": { + "External id": 1427356,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364371.886, "dur": 0.451, + "args": { + "External id": 1427357,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364373.869, "dur": 0.408, + "args": { + "External id": 1427358,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364376.226, "dur": 3.484, + "args": { + "External id": 1427359,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364381.557, "dur": 0.411, + "args": { + "External id": 1427360,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364383.530, "dur": 0.294, + "args": { + "External id": 1427361,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850364404.266, "dur": 64.528, + "args": { + "External id": 1427362,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850364505.268, "dur": 143.731, + "args": { + "External id": 1427363,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850364517.136, "dur": 5.585, + "args": { + "External id": 1427364,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850364528.651, "dur": 12.067, + "args": { + "External id": 1427365,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850364533.796, "dur": 6.409, + "args": { + "External id": 1427366,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364538.130, "dur": 0.672, + "args": { + "External id": 1427367,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850364548.871, "dur": 37.593, + "args": { + "External id": 1427368,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364551.956, "dur": 1.808, + "args": { + "External id": 1427369,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364555.392, "dur": 0.528, + "args": { + "External id": 1427370,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364557.566, "dur": 0.531, + "args": { + "External id": 1427371,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364561.615, "dur": 2.889, + "args": { + "External id": 1427372,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364566.286, "dur": 0.399, + "args": { + "External id": 1427373,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364568.472, "dur": 0.321, + "args": { + "External id": 1427374,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364572.051, "dur": 0.319, + "args": { + "External id": 1427375,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364574.494, "dur": 0.525, + "args": { + "External id": 1427376,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850364580.218, "dur": 1.523, + "args": { + "External id": 1427377,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850364599.431, "dur": 39.461, + "args": { + "External id": 1427378,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850364709.992, "dur": 484.846, + "args": { + "External id": 1427379,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850364745.513, "dur": 442.317, + "args": { + "External id": 1427380,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13816, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850364757.147, "dur": 423.730, + "args": { + "External id": 1427381,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850365225.735, "dur": 2.827, + "args": { + "External id": 1427382,"Record function id": 0, "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": 13818, "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": 2338706, "tid": 2338706, + "ts": 6413850365340.312, "dur": 28869.661, + "args": { + "External id": 1427383,"Record function id": 0, "Ev Idx": 13819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365463.427, "dur": 7.628, + "args": { + "External id": 1427384,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365475.574, "dur": 1.083, + "args": { + "External id": 1427385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365478.817, "dur": 3.396, + "args": { + "External id": 1427386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365484.265, "dur": 1.062, + "args": { + "External id": 1427387,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365487.093, "dur": 0.761, + "args": { + "External id": 1427388,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365489.442, "dur": 0.829, + "args": { + "External id": 1427389,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365492.348, "dur": 0.896, + "args": { + "External id": 1427390,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365495.097, "dur": 2.178, + "args": { + "External id": 1427391,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365499.016, "dur": 0.795, + "args": { + "External id": 1427392,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850365503.770, "dur": 0.944, + "args": { + "External id": 1427393,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850365525.740, "dur": 28620.406, + "args": { + "External id": 1427394,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850365551.818, "dur": 28582.567, + "args": { + "External id": 1427395,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850365568.124, "dur": 17.804, + "args": { + "External id": 1427396,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850365589.985, "dur": 28490.268, + "args": { + "External id": 1427397,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850365593.133, "dur": 28485.755, + "args": { + "External id": 1427398,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850365599.612, "dur": 6.401, + "args": { + "External id": 1427399,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850365608.084, "dur": 28439.784, + "args": { + "External id": 1427400,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850394381.294, "dur": 40.046, + "args": { + "External id": 1427401,"Sequence number": 15348703, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13837 + } + }, + { + "ph": "s", "id": 179, "pid": 2338706, "tid": 2338706, "ts": 6413850394381.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850394402.218, "dur": 13.174, + "args": { + "External id": 1427402,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850394408.206, "dur": 6.999, + "args": { + "External id": 1427403,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850394500.199, "dur": 83.599, + "args": { + "External id": 1427404,"Record function id": 0, "Ev Idx": 13840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850394585.288, "dur": 1376.930, + "args": { + "External id": 1427405,"Record function id": 0, "Ev Idx": 13841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850394628.855, "dur": 1316.480, + "args": { + "External id": 1427406,"Sequence number": 15348704, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13842 + } + }, + { + "ph": "s", "id": 178, "pid": 2338706, "tid": 2338706, "ts": 6413850394628.855, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850394719.720, "dur": 60.805, + "args": { + "External id": 1427407,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850394796.465, "dur": 119.359, + "args": { + "External id": 1427408,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850394931.418, "dur": 65.222, + "args": { + "External id": 1427409,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850395014.212, "dur": 99.566, + "args": { + "External id": 1427410,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850395162.272, "dur": 39.724, + "args": { + "External id": 1427411,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850395229.503, "dur": 22.078, + "args": { + "External id": 1427412,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850395280.030, "dur": 154.683, + "args": { + "External id": 1427413,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850395338.483, "dur": 15.859, + "args": { + "External id": 1427414,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850395346.360, "dur": 7.040, + "args": { + "External id": 1427415,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850395358.106, "dur": 4.719, + "args": { + "External id": 1427416,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850395364.712, "dur": 1.838, + "args": { + "External id": 1427417,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850395369.707, "dur": 4.734, + "args": { + "External id": 1427418,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850395447.727, "dur": 67.061, + "args": { + "External id": 1427419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850395552.363, "dur": 33.485, + "args": { + "External id": 1427420,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850395597.722, "dur": 48.784, + "args": { + "External id": 1427421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850395657.887, "dur": 41.083, + "args": { + "External id": 1427422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850395723.317, "dur": 46.205, + "args": { + "External id": 1427423,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850395778.090, "dur": 41.874, + "args": { + "External id": 1427424,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850395842.589, "dur": 19.995, + "args": { + "External id": 1427425,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13861 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 2338706, "tid": 2338706, + "ts": 6413850396101.619, "dur": 98.172, + "args": { + "External id": 1427426,"Record function id": 0, "Ev Idx": 13862 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850396296.068, "dur": 58.180, + "args": { + "External id": 1427427,"Record function id": 0, "Ev Idx": 13863 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338706, "tid": 2338706, + "ts": 6413850396365.527, "dur": 30116.789, + "args": { + "External id": 1427428,"Record function id": 0, "Ev Idx": 13864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338706, "tid": 2338706, + "ts": 6413850396375.729, "dur": 1227.600, + "args": { + "External id": 1427429,"Record function id": 0, "Ev Idx": 13865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850396476.967, "dur": 11.830, + "args": { + "External id": 1427430,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850396504.173, "dur": 45.590, + "args": { + "External id": 1427431,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396510.888, "dur": 5.986, + "args": { + "External id": 1427432,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396521.013, "dur": 0.750, + "args": { + "External id": 1427433,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396524.031, "dur": 0.636, + "args": { + "External id": 1427434,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396526.607, "dur": 0.471, + "args": { + "External id": 1427435,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396530.059, "dur": 0.664, + "args": { + "External id": 1427436,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396532.337, "dur": 0.546, + "args": { + "External id": 1427437,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396534.604, "dur": 4.526, + "args": { + "External id": 1427438,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396540.767, "dur": 0.359, + "args": { + "External id": 1427439,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396542.754, "dur": 0.355, + "args": { + "External id": 1427440,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850396563.277, "dur": 66.049, + "args": { + "External id": 1427441,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850396668.035, "dur": 249.458, + "args": { + "External id": 1427442,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850396680.811, "dur": 4.464, + "args": { + "External id": 1427443,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850396691.398, "dur": 12.866, + "args": { + "External id": 1427444,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850396696.750, "dur": 7.044, + "args": { + "External id": 1427445,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396701.405, "dur": 0.898, + "args": { + "External id": 1427446,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850396712.245, "dur": 33.566, + "args": { + "External id": 1427447,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396714.712, "dur": 2.119, + "args": { + "External id": 1427448,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396718.679, "dur": 0.399, + "args": { + "External id": 1427449,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396720.794, "dur": 0.424, + "args": { + "External id": 1427450,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396725.211, "dur": 2.408, + "args": { + "External id": 1427451,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396729.275, "dur": 0.446, + "args": { + "External id": 1427452,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396731.322, "dur": 0.577, + "args": { + "External id": 1427453,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396735.338, "dur": 0.436, + "args": { + "External id": 1427454,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396737.683, "dur": 0.329, + "args": { + "External id": 1427455,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850396740.001, "dur": 1.629, + "args": { + "External id": 1427456,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850396858.816, "dur": 47.599, + "args": { + "External id": 1427457,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850397007.150, "dur": 476.889, + "args": { + "External id": 1427458,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850397043.494, "dur": 434.193, + "args": { + "External id": 1427459,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13895, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850397092.741, "dur": 378.710, + "args": { + "External id": 1427460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850397513.819, "dur": 2.553, + "args": { + "External id": 1427461,"Record function id": 0, "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": 13897, "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": 2338706, "tid": 2338706, + "ts": 6413850397629.045, "dur": 28597.676, + "args": { + "External id": 1427462,"Record function id": 0, "Ev Idx": 13898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397749.819, "dur": 7.456, + "args": { + "External id": 1427463,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397761.300, "dur": 1.127, + "args": { + "External id": 1427464,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397764.443, "dur": 3.518, + "args": { + "External id": 1427465,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397770.120, "dur": 0.910, + "args": { + "External id": 1427466,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397772.559, "dur": 1.024, + "args": { + "External id": 1427467,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397774.983, "dur": 1.276, + "args": { + "External id": 1427468,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397778.519, "dur": 0.842, + "args": { + "External id": 1427469,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397781.326, "dur": 2.498, + "args": { + "External id": 1427470,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397785.454, "dur": 1.080, + "args": { + "External id": 1427471,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850397790.546, "dur": 0.790, + "args": { + "External id": 1427472,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850397812.937, "dur": 28347.600, + "args": { + "External id": 1427473,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850397832.415, "dur": 28316.427, + "args": { + "External id": 1427474,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850397854.072, "dur": 19.472, + "args": { + "External id": 1427475,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850397877.841, "dur": 28218.590, + "args": { + "External id": 1427476,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850397880.813, "dur": 28214.655, + "args": { + "External id": 1427477,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850397886.633, "dur": 6.041, + "args": { + "External id": 1427478,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850397894.706, "dur": 28195.460, + "args": { + "External id": 1427479,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850426405.682, "dur": 45.224, + "args": { + "External id": 1427480,"Sequence number": 15348705, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13916 + } + }, + { + "ph": "s", "id": 177, "pid": 2338706, "tid": 2338706, "ts": 6413850426405.682, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850426431.756, "dur": 13.233, + "args": { + "External id": 1427481,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850426437.549, "dur": 7.201, + "args": { + "External id": 1427482,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850426530.149, "dur": 81.470, + "args": { + "External id": 1427483,"Record function id": 0, "Ev Idx": 13919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850426613.172, "dur": 1327.283, + "args": { + "External id": 1427484,"Record function id": 0, "Ev Idx": 13920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850426662.164, "dur": 1261.337, + "args": { + "External id": 1427485,"Sequence number": 15348706, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 13921 + } + }, + { + "ph": "s", "id": 176, "pid": 2338706, "tid": 2338706, "ts": 6413850426662.164, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850426745.076, "dur": 57.482, + "args": { + "External id": 1427486,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850426817.048, "dur": 121.105, + "args": { + "External id": 1427487,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850426953.494, "dur": 68.300, + "args": { + "External id": 1427488,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850427036.438, "dur": 82.994, + "args": { + "External id": 1427489,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 13925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850427165.923, "dur": 32.760, + "args": { + "External id": 1427490,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850427223.990, "dur": 20.884, + "args": { + "External id": 1427491,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 13927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850427273.428, "dur": 153.845, + "args": { + "External id": 1427492,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 13928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850427331.384, "dur": 16.583, + "args": { + "External id": 1427493,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 13929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850427339.251, "dur": 7.698, + "args": { + "External id": 1427494,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850427351.405, "dur": 5.157, + "args": { + "External id": 1427495,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850427357.962, "dur": 1.765, + "args": { + "External id": 1427496,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850427362.735, "dur": 6.169, + "args": { + "External id": 1427497,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850427440.878, "dur": 63.336, + "args": { + "External id": 1427498,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 13934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850427541.392, "dur": 36.231, + "args": { + "External id": 1427499,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 13935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850427589.640, "dur": 49.143, + "args": { + "External id": 1427500,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850427649.646, "dur": 41.028, + "args": { + "External id": 1427501,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 13937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850427719.009, "dur": 31.776, + "args": { + "External id": 1427502,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 13938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850427758.443, "dur": 40.644, + "args": { + "External id": 1427503,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 13939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850427820.348, "dur": 19.094, + "args": { + "External id": 1427504,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 13940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 2338706, "tid": 2338706, + "ts": 6413850428038.182, "dur": 134.025, + "args": { + "External id": 1427505,"Record function id": 0, "Ev Idx": 13941 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850428271.539, "dur": 60.538, + "args": { + "External id": 1427506,"Record function id": 0, "Ev Idx": 13942 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338706, "tid": 2338706, + "ts": 6413850428343.535, "dur": 31437.173, + "args": { + "External id": 1427507,"Record function id": 0, "Ev Idx": 13943 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338706, "tid": 2338706, + "ts": 6413850428355.153, "dur": 1098.603, + "args": { + "External id": 1427508,"Record function id": 0, "Ev Idx": 13944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850428451.276, "dur": 10.917, + "args": { + "External id": 1427509,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850428477.355, "dur": 44.605, + "args": { + "External id": 1427510,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428484.565, "dur": 2.637, + "args": { + "External id": 1427511,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428492.141, "dur": 0.526, + "args": { + "External id": 1427512,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428494.826, "dur": 0.765, + "args": { + "External id": 1427513,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428497.215, "dur": 0.540, + "args": { + "External id": 1427514,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428501.124, "dur": 0.617, + "args": { + "External id": 1427515,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428503.461, "dur": 0.923, + "args": { + "External id": 1427516,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428506.287, "dur": 4.279, + "args": { + "External id": 1427517,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428512.822, "dur": 0.339, + "args": { + "External id": 1427518,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428514.647, "dur": 0.672, + "args": { + "External id": 1427519,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850428536.311, "dur": 66.353, + "args": { + "External id": 1427520,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850428640.209, "dur": 144.527, + "args": { + "External id": 1427521,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 13957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850428653.091, "dur": 4.842, + "args": { + "External id": 1427522,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850428664.316, "dur": 11.801, + "args": { + "External id": 1427523,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850428669.496, "dur": 6.141, + "args": { + "External id": 1427524,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 13960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428673.568, "dur": 0.783, + "args": { + "External id": 1427525,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 13961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850428684.166, "dur": 36.597, + "args": { + "External id": 1427526,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 13962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428687.196, "dur": 2.234, + "args": { + "External id": 1427527,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428691.338, "dur": 0.462, + "args": { + "External id": 1427528,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428693.523, "dur": 0.428, + "args": { + "External id": 1427529,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428697.803, "dur": 2.578, + "args": { + "External id": 1427530,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428701.900, "dur": 0.575, + "args": { + "External id": 1427531,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428704.065, "dur": 0.554, + "args": { + "External id": 1427532,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428706.573, "dur": 0.417, + "args": { + "External id": 1427533,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428708.471, "dur": 0.354, + "args": { + "External id": 1427534,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850428710.991, "dur": 2.099, + "args": { + "External id": 1427535,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 13971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850428733.843, "dur": 39.274, + "args": { + "External id": 1427536,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 13972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850428848.454, "dur": 484.511, + "args": { + "External id": 1427537,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 13973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850428891.164, "dur": 434.908, + "args": { + "External id": 1427538,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 13974, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850428903.058, "dur": 413.256, + "args": { + "External id": 1427539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 13975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850429365.046, "dur": 2.768, + "args": { + "External id": 1427540,"Record function id": 0, "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": 13976, "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": 2338706, "tid": 2338706, + "ts": 6413850429477.965, "dur": 30047.705, + "args": { + "External id": 1427541,"Record function id": 0, "Ev Idx": 13977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429601.981, "dur": 7.877, + "args": { + "External id": 1427542,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 13978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429619.281, "dur": 1.287, + "args": { + "External id": 1427543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429622.851, "dur": 3.860, + "args": { + "External id": 1427544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429630.774, "dur": 1.055, + "args": { + "External id": 1427545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429633.571, "dur": 0.995, + "args": { + "External id": 1427546,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 13982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429636.232, "dur": 1.045, + "args": { + "External id": 1427547,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 13983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429639.666, "dur": 1.100, + "args": { + "External id": 1427548,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 13984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429645.041, "dur": 2.174, + "args": { + "External id": 1427549,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429649.063, "dur": 0.978, + "args": { + "External id": 1427550,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850429651.817, "dur": 0.914, + "args": { + "External id": 1427551,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 13987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850429674.395, "dur": 29792.161, + "args": { + "External id": 1427552,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850429693.533, "dur": 29763.560, + "args": { + "External id": 1427553,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 13989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850429709.199, "dur": 19.513, + "args": { + "External id": 1427554,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850429735.263, "dur": 29676.422, + "args": { + "External id": 1427555,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 13991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850429738.300, "dur": 29672.359, + "args": { + "External id": 1427556,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 13992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850429744.901, "dur": 6.025, + "args": { + "External id": 1427557,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850429752.741, "dur": 29653.216, + "args": { + "External id": 1427558,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 13994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850459700.847, "dur": 45.117, + "args": { + "External id": 1427559,"Sequence number": 15348707, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 13995 + } + }, + { + "ph": "s", "id": 175, "pid": 2338706, "tid": 2338706, "ts": 6413850459700.847, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850459723.913, "dur": 15.758, + "args": { + "External id": 1427560,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 13996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850459730.619, "dur": 7.586, + "args": { + "External id": 1427561,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 13997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850459834.089, "dur": 83.625, + "args": { + "External id": 1427562,"Record function id": 0, "Ev Idx": 13998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850459919.319, "dur": 1446.382, + "args": { + "External id": 1427563,"Record function id": 0, "Ev Idx": 13999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850459967.470, "dur": 1381.399, + "args": { + "External id": 1427564,"Sequence number": 15348708, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 14000 + } + }, + { + "ph": "s", "id": 174, "pid": 2338706, "tid": 2338706, "ts": 6413850459967.470, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850460121.113, "dur": 64.377, + "args": { + "External id": 1427565,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850460207.575, "dur": 118.735, + "args": { + "External id": 1427566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850460342.369, "dur": 50.179, + "args": { + "External id": 1427567,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850460403.813, "dur": 35.641, + "args": { + "External id": 1427568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850460472.959, "dur": 33.874, + "args": { + "External id": 1427569,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850460532.556, "dur": 19.731, + "args": { + "External id": 1427570,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850460578.977, "dur": 159.720, + "args": { + "External id": 1427571,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850460640.395, "dur": 16.546, + "args": { + "External id": 1427572,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850460648.344, "dur": 7.625, + "args": { + "External id": 1427573,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850460661.314, "dur": 4.534, + "args": { + "External id": 1427574,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850460667.697, "dur": 1.817, + "args": { + "External id": 1427575,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850460672.835, "dur": 5.318, + "args": { + "External id": 1427576,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850460752.418, "dur": 55.676, + "args": { + "External id": 1427577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850460847.596, "dur": 34.673, + "args": { + "External id": 1427578,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850460894.034, "dur": 51.583, + "args": { + "External id": 1427579,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850460957.277, "dur": 67.125, + "args": { + "External id": 1427580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850461111.914, "dur": 39.263, + "args": { + "External id": 1427581,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 14017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850461163.045, "dur": 52.813, + "args": { + "External id": 1427582,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 14018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850461241.687, "dur": 24.166, + "args": { + "External id": 1427583,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 14019 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 2338706, "tid": 2338706, + "ts": 6413850461446.236, "dur": 91.780, + "args": { + "External id": 1427584,"Record function id": 0, "Ev Idx": 14020 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413850461625.626, "dur": 53.693, + "args": { + "External id": 1427585,"Record function id": 0, "Ev Idx": 14021 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338706, "tid": 2338706, + "ts": 6413850461690.086, "dur": 32240.351, + "args": { + "External id": 1427586,"Record function id": 0, "Ev Idx": 14022 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338706, "tid": 2338706, + "ts": 6413850461701.297, "dur": 1243.204, + "args": { + "External id": 1427587,"Record function id": 0, "Ev Idx": 14023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850461797.927, "dur": 11.031, + "args": { + "External id": 1427588,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850461825.687, "dur": 40.033, + "args": { + "External id": 1427589,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 14025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461831.767, "dur": 2.637, + "args": { + "External id": 1427590,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461839.061, "dur": 0.408, + "args": { + "External id": 1427591,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461841.472, "dur": 0.640, + "args": { + "External id": 1427592,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461843.602, "dur": 0.707, + "args": { + "External id": 1427593,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461847.417, "dur": 0.629, + "args": { + "External id": 1427594,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461849.772, "dur": 0.446, + "args": { + "External id": 1427595,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461851.885, "dur": 3.131, + "args": { + "External id": 1427596,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461856.439, "dur": 0.299, + "args": { + "External id": 1427597,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850461858.518, "dur": 0.480, + "args": { + "External id": 1427598,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850461879.101, "dur": 63.280, + "args": { + "External id": 1427599,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 14035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413850462001.246, "dur": 244.402, + "args": { + "External id": 1427600,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 14036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850462016.980, "dur": 6.435, + "args": { + "External id": 1427601,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413850462030.348, "dur": 13.000, + "args": { + "External id": 1427602,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 14038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850462035.414, "dur": 7.426, + "args": { + "External id": 1427603,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 14039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462039.900, "dur": 1.114, + "args": { + "External id": 1427604,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 14040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413850462052.393, "dur": 101.555, + "args": { + "External id": 1427605,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 14041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462104.754, "dur": 3.865, + "args": { + "External id": 1427606,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462115.134, "dur": 0.890, + "args": { + "External id": 1427607,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462119.126, "dur": 1.099, + "args": { + "External id": 1427608,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462124.374, "dur": 3.351, + "args": { + "External id": 1427609,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462130.062, "dur": 0.845, + "args": { + "External id": 1427610,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462133.468, "dur": 0.646, + "args": { + "External id": 1427611,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462138.225, "dur": 0.989, + "args": { + "External id": 1427612,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462142.027, "dur": 0.719, + "args": { + "External id": 1427613,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850462145.239, "dur": 2.429, + "args": { + "External id": 1427614,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 14050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850462178.017, "dur": 55.520, + "args": { + "External id": 1427615,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 14051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413850462318.119, "dur": 511.307, + "args": { + "External id": 1427616,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 14052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850462356.726, "dur": 466.589, + "args": { + "External id": 1427617,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 14053, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413850462369.367, "dur": 447.553, + "args": { + "External id": 1427618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 14054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413850462857.052, "dur": 3.181, + "args": { + "External id": 1427619,"Record function id": 0, "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": 14055, "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": 2338706, "tid": 2338706, + "ts": 6413850462970.242, "dur": 30687.766, + "args": { + "External id": 1427620,"Record function id": 0, "Ev Idx": 14056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463165.080, "dur": 8.491, + "args": { + "External id": 1427621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 14057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463178.134, "dur": 1.111, + "args": { + "External id": 1427622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463181.510, "dur": 3.179, + "args": { + "External id": 1427623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 14059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463186.910, "dur": 1.035, + "args": { + "External id": 1427624,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 14060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463189.448, "dur": 1.040, + "args": { + "External id": 1427625,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 14061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463191.832, "dur": 1.038, + "args": { + "External id": 1427626,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 14062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463196.897, "dur": 1.135, + "args": { + "External id": 1427627,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463199.866, "dur": 2.286, + "args": { + "External id": 1427628,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 14064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463204.045, "dur": 1.018, + "args": { + "External id": 1427629,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 14065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850463206.829, "dur": 0.751, + "args": { + "External id": 1427630,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 14066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850463233.504, "dur": 30361.821, + "args": { + "External id": 1427631,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 14067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850463254.756, "dur": 30329.625, + "args": { + "External id": 1427632,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 14068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850463282.296, "dur": 21.215, + "args": { + "External id": 1427633,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850463308.665, "dur": 30228.562, + "args": { + "External id": 1427634,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 14070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850463311.786, "dur": 30224.161, + "args": { + "External id": 1427635,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 14071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850463317.322, "dur": 6.618, + "args": { + "External id": 1427636,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850463325.718, "dur": 30205.816, + "args": { + "External id": 1427637,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 14073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850493854.784, "dur": 43.018, + "args": { + "External id": 1427638,"Sequence number": 15348709, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 14074 + } + }, + { + "ph": "s", "id": 173, "pid": 2338706, "tid": 2338706, "ts": 6413850493854.784, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850493877.139, "dur": 13.481, + "args": { + "External id": 1427639,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 14075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850493883.185, "dur": 7.116, + "args": { + "External id": 1427640,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850493999.339, "dur": 133.255, + "args": { + "External id": 1427641,"Record function id": 0, "Ev Idx": 14077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413850494136.279, "dur": 1414.805, + "args": { + "External id": 1427642,"Record function id": 0, "Ev Idx": 14078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850494194.114, "dur": 1339.553, + "args": { + "External id": 1427643,"Sequence number": 15348710, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 14079 + } + }, + { + "ph": "s", "id": 172, "pid": 2338706, "tid": 2338706, "ts": 6413850494194.114, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850494285.795, "dur": 64.383, + "args": { + "External id": 1427644,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850494368.693, "dur": 119.594, + "args": { + "External id": 1427645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850494504.625, "dur": 41.597, + "args": { + "External id": 1427646,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850494555.588, "dur": 33.759, + "args": { + "External id": 1427647,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 14083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850494621.579, "dur": 30.924, + "args": { + "External id": 1427648,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413850494680.200, "dur": 24.718, + "args": { + "External id": 1427649,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 14085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850494730.590, "dur": 157.996, + "args": { + "External id": 1427650,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850494788.012, "dur": 15.891, + "args": { + "External id": 1427651,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850494795.950, "dur": 7.031, + "args": { + "External id": 1427652,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850494808.173, "dur": 4.372, + "args": { + "External id": 1427653,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850494813.909, "dur": 1.649, + "args": { + "External id": 1427654,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850494818.701, "dur": 6.336, + "args": { + "External id": 1427655,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850494901.844, "dur": 56.862, + "args": { + "External id": 1427656,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 14092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413850495021.362, "dur": 111.306, + "args": { + "External id": 1427657,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 14093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850495156.357, "dur": 65.063, + "args": { + "External id": 1427658,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850495234.684, "dur": 42.155, + "args": { + "External id": 1427659,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 14095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850495311.083, "dur": 37.220, + "args": { + "External id": 1427660,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 14096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850495356.688, "dur": 43.834, + "args": { + "External id": 1427661,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 14097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413850495422.976, "dur": 22.766, + "args": { + "External id": 1427662,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 14098 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 2338706, "tid": 2338706, + "ts": 6413850495628.047, "dur": 41.946, + "args": { + "External id": 1427663,"Record function id": 0, "Ev Idx": 14099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850495832.071, "dur": 414.894, + "args": { + "External id": 1427664,"Sequence number": 15348711, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14100 + } + }, + { + "ph": "s", "id": 171, "pid": 2338706, "tid": 2338706, "ts": 6413850495832.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850495870.320, "dur": 9.183, + "args": { + "External id": 1427665,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850495872.875, "dur": 6.329, + "args": { + "External id": 1427666,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850495890.905, "dur": 14.570, + "args": { + "External id": 1427667,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850495895.011, "dur": 9.801, + "args": { + "External id": 1427668,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850495916.607, "dur": 5.528, + "args": { + "External id": 1427669,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496218.710, "dur": 9.429, + "args": { + "External id": 1427670,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496222.100, "dur": 5.634, + "args": { + "External id": 1427671,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850496280.829, "dur": 173.311, + "args": { + "External id": 1427672,"Sequence number": 15348712, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850496284.418, "dur": 20.239, + "args": { + "External id": 1427673,"Sequence number": 15348712, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14109 + } + }, + { + "ph": "s", "id": 170, "pid": 2338706, "tid": 2338706, "ts": 6413850496284.418, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850496291.887, "dur": 10.373, + "args": { + "External id": 1427674,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850496299.496, "dur": 2.367, + "args": { + "External id": 1427675,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850496307.773, "dur": 145.989, + "args": { + "External id": 1427676,"Sequence number": 15348713, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496311.714, "dur": 5.597, + "args": { + "External id": 1427677,"Sequence number": 15348713, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496312.967, "dur": 4.099, + "args": { + "External id": 1427678,"Sequence number": 15348713, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14114 + } + }, + { + "ph": "s", "id": 169, "pid": 2338706, "tid": 2338706, "ts": 6413850496312.967, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850496322.078, "dur": 111.871, + "args": { + "External id": 1427679,"Sequence number": 15348714, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14115 + } + }, + { + "ph": "s", "id": 168, "pid": 2338706, "tid": 2338706, "ts": 6413850496322.078, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496442.364, "dur": 10.139, + "args": { + "External id": 1427680,"Sequence number": 15348715, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14116 + } + }, + { + "ph": "s", "id": 167, "pid": 2338706, "tid": 2338706, "ts": 6413850496442.364, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850496466.002, "dur": 72.828, + "args": { + "External id": 1427681,"Sequence number": 15348716, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850496466.799, "dur": 8.843, + "args": { + "External id": 1427682,"Sequence number": 15348716, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14118 + } + }, + { + "ph": "s", "id": 166, "pid": 2338706, "tid": 2338706, "ts": 6413850496466.799, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850496468.786, "dur": 5.558, + "args": { + "External id": 1427683,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850496473.190, "dur": 0.949, + "args": { + "External id": 1427684,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850496476.470, "dur": 62.015, + "args": { + "External id": 1427685,"Sequence number": 15348717, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496477.701, "dur": 4.809, + "args": { + "External id": 1427686,"Sequence number": 15348717, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496478.565, "dur": 3.781, + "args": { + "External id": 1427687,"Sequence number": 15348717, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14123 + } + }, + { + "ph": "s", "id": 165, "pid": 2338706, "tid": 2338706, "ts": 6413850496478.565, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850496483.404, "dur": 48.106, + "args": { + "External id": 1427688,"Sequence number": 15348718, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14124 + } + }, + { + "ph": "s", "id": 164, "pid": 2338706, "tid": 2338706, "ts": 6413850496483.404, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496533.960, "dur": 4.030, + "args": { + "External id": 1427689,"Sequence number": 15348719, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14125 + } + }, + { + "ph": "s", "id": 163, "pid": 2338706, "tid": 2338706, "ts": 6413850496533.960, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850496547.863, "dur": 70.035, + "args": { + "External id": 1427690,"Sequence number": 15348720, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850496548.467, "dur": 5.454, + "args": { + "External id": 1427691,"Sequence number": 15348720, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14127 + } + }, + { + "ph": "s", "id": 162, "pid": 2338706, "tid": 2338706, "ts": 6413850496548.467, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850496549.708, "dur": 3.051, + "args": { + "External id": 1427692,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850496551.949, "dur": 0.626, + "args": { + "External id": 1427693,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850496556.828, "dur": 60.776, + "args": { + "External id": 1427694,"Sequence number": 15348721, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496558.042, "dur": 5.111, + "args": { + "External id": 1427695,"Sequence number": 15348721, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496559.127, "dur": 3.867, + "args": { + "External id": 1427696,"Sequence number": 15348721, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14132 + } + }, + { + "ph": "s", "id": 161, "pid": 2338706, "tid": 2338706, "ts": 6413850496559.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850496563.808, "dur": 45.124, + "args": { + "External id": 1427697,"Sequence number": 15348722, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14133 + } + }, + { + "ph": "s", "id": 160, "pid": 2338706, "tid": 2338706, "ts": 6413850496563.808, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496611.247, "dur": 5.916, + "args": { + "External id": 1427698,"Sequence number": 15348723, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14134 + } + }, + { + "ph": "s", "id": 159, "pid": 2338706, "tid": 2338706, "ts": 6413850496611.247, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496643.321, "dur": 4.400, + "args": { + "External id": 1427699,"Sequence number": 15348724, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496644.868, "dur": 2.676, + "args": { + "External id": 1427700,"Sequence number": 15348724, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14136 + } + }, + { + "ph": "s", "id": 158, "pid": 2338706, "tid": 2338706, "ts": 6413850496644.868, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496656.864, "dur": 3.625, + "args": { + "External id": 1427701,"Sequence number": 15348725, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496658.255, "dur": 2.078, + "args": { + "External id": 1427702,"Sequence number": 15348725, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14138 + } + }, + { + "ph": "s", "id": 157, "pid": 2338706, "tid": 2338706, "ts": 6413850496658.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850496668.135, "dur": 4.438, + "args": { + "External id": 1427703,"Sequence number": 15348726, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850496669.301, "dur": 3.108, + "args": { + "External id": 1427704,"Sequence number": 15348726, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14140 + } + }, + { + "ph": "s", "id": 156, "pid": 2338706, "tid": 2338706, "ts": 6413850496669.301, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850496715.762, "dur": 211.744, + "args": { + "External id": 1427705,"Sequence number": 15348727, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14141 + } + }, + { + "ph": "s", "id": 155, "pid": 2338706, "tid": 2338706, "ts": 6413850496715.762, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850496742.654, "dur": 11.360, + "args": { + "External id": 1427706,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850496746.741, "dur": 6.650, + "args": { + "External id": 1427707,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850496943.628, "dur": 214.185, + "args": { + "External id": 1427708,"Sequence number": 15348728, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14144 + } + }, + { + "ph": "s", "id": 154, "pid": 2338706, "tid": 2338706, "ts": 6413850496943.628, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850496959.993, "dur": 8.750, + "args": { + "External id": 1427709,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850496963.631, "dur": 4.516, + "args": { + "External id": 1427710,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413850497199.366, "dur": 226.212, + "args": { + "External id": 1427711,"Sequence number": 15348729, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14147 + } + }, + { + "ph": "s", "id": 153, "pid": 2338706, "tid": 2338706, "ts": 6413850497199.366, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850497235.180, "dur": 155.440, + "args": { + "External id": 1427712,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850497295.608, "dur": 11.476, + "args": { + "External id": 1427713,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850497299.867, "dur": 6.627, + "args": { + "External id": 1427714,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850497314.871, "dur": 5.250, + "args": { + "External id": 1427715,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850497323.158, "dur": 1.542, + "args": { + "External id": 1427716,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850497327.920, "dur": 3.500, + "args": { + "External id": 1427717,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413850497407.410, "dur": 6.849, + "args": { + "External id": 1427718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497433.191, "dur": 7.697, + "args": { + "External id": 1427719,"Sequence number": 15348730, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497435.418, "dur": 5.180, + "args": { + "External id": 1427720,"Sequence number": 15348730, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14156 + } + }, + { + "ph": "s", "id": 152, "pid": 2338706, "tid": 2338706, "ts": 6413850497435.418, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850497458.617, "dur": 127.759, + "args": { + "External id": 1427721,"Sequence number": 15348731, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850497460.325, "dur": 10.317, + "args": { + "External id": 1427722,"Sequence number": 15348731, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14158 + } + }, + { + "ph": "s", "id": 151, "pid": 2338706, "tid": 2338706, "ts": 6413850497460.325, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850497463.420, "dur": 5.740, + "args": { + "External id": 1427723,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850497466.523, "dur": 2.275, + "args": { + "External id": 1427724,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850497472.168, "dur": 113.855, + "args": { + "External id": 1427725,"Sequence number": 15348732, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497476.769, "dur": 4.068, + "args": { + "External id": 1427726,"Sequence number": 15348732, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497477.923, "dur": 2.750, + "args": { + "External id": 1427727,"Sequence number": 15348732, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14163 + } + }, + { + "ph": "s", "id": 150, "pid": 2338706, "tid": 2338706, "ts": 6413850497477.923, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850497481.850, "dur": 96.396, + "args": { + "External id": 1427728,"Sequence number": 15348733, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14164 + } + }, + { + "ph": "s", "id": 149, "pid": 2338706, "tid": 2338706, "ts": 6413850497481.850, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497581.309, "dur": 3.953, + "args": { + "External id": 1427729,"Sequence number": 15348734, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14165 + } + }, + { + "ph": "s", "id": 148, "pid": 2338706, "tid": 2338706, "ts": 6413850497581.309, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850497627.058, "dur": 257.418, + "args": { + "External id": 1427730,"Sequence number": 15348735, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14166 + } + }, + { + "ph": "s", "id": 147, "pid": 2338706, "tid": 2338706, "ts": 6413850497627.058, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497651.116, "dur": 3.027, + "args": { + "External id": 1427731,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497652.325, "dur": 1.652, + "args": { + "External id": 1427732,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850497659.931, "dur": 8.343, + "args": { + "External id": 1427733,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497661.657, "dur": 6.495, + "args": { + "External id": 1427734,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497664.801, "dur": 3.243, + "args": { + "External id": 1427735,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850497677.416, "dur": 7.684, + "args": { + "External id": 1427736,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850497680.115, "dur": 4.635, + "args": { + "External id": 1427737,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850497692.117, "dur": 3.109, + "args": { + "External id": 1427738,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850497701.370, "dur": 3.552, + "args": { + "External id": 1427739,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497857.460, "dur": 3.652, + "args": { + "External id": 1427740,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497858.906, "dur": 1.972, + "args": { + "External id": 1427741,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497867.095, "dur": 2.916, + "args": { + "External id": 1427742,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497868.555, "dur": 1.344, + "args": { + "External id": 1427743,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850497906.336, "dur": 136.286, + "args": { + "External id": 1427744,"Sequence number": 15348736, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850497907.700, "dur": 8.713, + "args": { + "External id": 1427745,"Sequence number": 15348736, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14181 + } + }, + { + "ph": "s", "id": 146, "pid": 2338706, "tid": 2338706, "ts": 6413850497907.700, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850497910.419, "dur": 4.629, + "args": { + "External id": 1427746,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850497913.237, "dur": 1.582, + "args": { + "External id": 1427747,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850497919.590, "dur": 122.651, + "args": { + "External id": 1427748,"Sequence number": 15348737, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850497921.617, "dur": 3.926, + "args": { + "External id": 1427749,"Sequence number": 15348737, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850497923.175, "dur": 2.231, + "args": { + "External id": 1427750,"Sequence number": 15348737, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14186 + } + }, + { + "ph": "s", "id": 145, "pid": 2338706, "tid": 2338706, "ts": 6413850497923.175, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850497926.548, "dur": 99.616, + "args": { + "External id": 1427751,"Sequence number": 15348738, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14187 + } + }, + { + "ph": "s", "id": 144, "pid": 2338706, "tid": 2338706, "ts": 6413850497926.548, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498030.713, "dur": 10.752, + "args": { + "External id": 1427752,"Sequence number": 15348739, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14188 + } + }, + { + "ph": "s", "id": 143, "pid": 2338706, "tid": 2338706, "ts": 6413850498030.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850498095.603, "dur": 98.553, + "args": { + "External id": 1427753,"Sequence number": 15348740, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850498097.660, "dur": 11.551, + "args": { + "External id": 1427754,"Sequence number": 15348740, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14190 + } + }, + { + "ph": "s", "id": 142, "pid": 2338706, "tid": 2338706, "ts": 6413850498097.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850498101.873, "dur": 5.046, + "args": { + "External id": 1427755,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850498104.786, "dur": 1.615, + "args": { + "External id": 1427756,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850498110.344, "dur": 83.517, + "args": { + "External id": 1427757,"Sequence number": 15348741, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498114.205, "dur": 5.826, + "args": { + "External id": 1427758,"Sequence number": 15348741, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498115.536, "dur": 4.224, + "args": { + "External id": 1427759,"Sequence number": 15348741, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14195 + } + }, + { + "ph": "s", "id": 141, "pid": 2338706, "tid": 2338706, "ts": 6413850498115.536, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850498120.828, "dur": 67.420, + "args": { + "External id": 1427760,"Sequence number": 15348742, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14196 + } + }, + { + "ph": "s", "id": 140, "pid": 2338706, "tid": 2338706, "ts": 6413850498120.828, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498190.616, "dur": 2.735, + "args": { + "External id": 1427761,"Sequence number": 15348743, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14197 + } + }, + { + "ph": "s", "id": 139, "pid": 2338706, "tid": 2338706, "ts": 6413850498190.616, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850498226.461, "dur": 189.479, + "args": { + "External id": 1427762,"Sequence number": 15348744, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14198 + } + }, + { + "ph": "s", "id": 138, "pid": 2338706, "tid": 2338706, "ts": 6413850498226.461, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850498277.706, "dur": 5.360, + "args": { + "External id": 1427763,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850498322.512, "dur": 75.525, + "args": { + "External id": 1427764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850498323.478, "dur": 7.618, + "args": { + "External id": 1427765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850498325.083, "dur": 4.927, + "args": { + "External id": 1427766,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850498328.801, "dur": 0.976, + "args": { + "External id": 1427767,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850498334.719, "dur": 62.967, + "args": { + "External id": 1427768,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498336.409, "dur": 2.927, + "args": { + "External id": 1427769,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498337.756, "dur": 1.477, + "args": { + "External id": 1427770,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850498340.401, "dur": 52.959, + "args": { + "External id": 1427771,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498395.825, "dur": 1.045, + "args": { + "External id": 1427772,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413850498428.458, "dur": 33.574, + "args": { + "External id": 1427773,"Sequence number": 15348745, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14209 + } + }, + { + "ph": "s", "id": 137, "pid": 2338706, "tid": 2338706, "ts": 6413850498428.458, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850498502.058, "dur": 230.843, + "args": { + "External id": 1427774,"Sequence number": 15348746, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14210 + } + }, + { + "ph": "s", "id": 136, "pid": 2338706, "tid": 2338706, "ts": 6413850498502.058, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498526.836, "dur": 4.090, + "args": { + "External id": 1427775,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498528.388, "dur": 2.224, + "args": { + "External id": 1427776,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850498540.929, "dur": 8.805, + "args": { + "External id": 1427777,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850498544.328, "dur": 4.954, + "args": { + "External id": 1427778,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850498557.393, "dur": 5.121, + "args": { + "External id": 1427779,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498712.376, "dur": 3.666, + "args": { + "External id": 1427780,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498714.133, "dur": 1.755, + "args": { + "External id": 1427781,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850498754.453, "dur": 102.361, + "args": { + "External id": 1427782,"Sequence number": 15348747, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850498755.556, "dur": 8.049, + "args": { + "External id": 1427783,"Sequence number": 15348747, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14219 + } + }, + { + "ph": "s", "id": 135, "pid": 2338706, "tid": 2338706, "ts": 6413850498755.556, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850498757.658, "dur": 4.300, + "args": { + "External id": 1427784,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850498760.280, "dur": 1.466, + "args": { + "External id": 1427785,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850498764.497, "dur": 91.883, + "args": { + "External id": 1427786,"Sequence number": 15348748, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498768.517, "dur": 6.606, + "args": { + "External id": 1427787,"Sequence number": 15348748, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498769.772, "dur": 5.120, + "args": { + "External id": 1427788,"Sequence number": 15348748, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14224 + } + }, + { + "ph": "s", "id": 134, "pid": 2338706, "tid": 2338706, "ts": 6413850498769.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850498776.329, "dur": 71.905, + "args": { + "External id": 1427789,"Sequence number": 15348749, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14225 + } + }, + { + "ph": "s", "id": 133, "pid": 2338706, "tid": 2338706, "ts": 6413850498776.329, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498851.059, "dur": 4.522, + "args": { + "External id": 1427790,"Sequence number": 15348750, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14226 + } + }, + { + "ph": "s", "id": 132, "pid": 2338706, "tid": 2338706, "ts": 6413850498851.059, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850498866.146, "dur": 80.015, + "args": { + "External id": 1427791,"Sequence number": 15348751, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850498869.371, "dur": 9.585, + "args": { + "External id": 1427792,"Sequence number": 15348751, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14228 + } + }, + { + "ph": "s", "id": 131, "pid": 2338706, "tid": 2338706, "ts": 6413850498869.371, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850498874.116, "dur": 3.631, + "args": { + "External id": 1427793,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850498876.521, "dur": 0.940, + "args": { + "External id": 1427794,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850498879.540, "dur": 66.284, + "args": { + "External id": 1427795,"Sequence number": 15348752, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498880.737, "dur": 5.607, + "args": { + "External id": 1427796,"Sequence number": 15348752, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498883.800, "dur": 2.401, + "args": { + "External id": 1427797,"Sequence number": 15348752, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14233 + } + }, + { + "ph": "s", "id": 130, "pid": 2338706, "tid": 2338706, "ts": 6413850498883.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850498886.955, "dur": 49.238, + "args": { + "External id": 1427798,"Sequence number": 15348753, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14234 + } + }, + { + "ph": "s", "id": 129, "pid": 2338706, "tid": 2338706, "ts": 6413850498886.955, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498938.472, "dur": 6.463, + "args": { + "External id": 1427799,"Sequence number": 15348754, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14235 + } + }, + { + "ph": "s", "id": 128, "pid": 2338706, "tid": 2338706, "ts": 6413850498938.472, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850498954.791, "dur": 99.367, + "args": { + "External id": 1427800,"Sequence number": 15348755, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850498955.738, "dur": 8.670, + "args": { + "External id": 1427801,"Sequence number": 15348755, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14237 + } + }, + { + "ph": "s", "id": 127, "pid": 2338706, "tid": 2338706, "ts": 6413850498955.738, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850498960.162, "dur": 3.127, + "args": { + "External id": 1427802,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850498962.343, "dur": 0.775, + "args": { + "External id": 1427803,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850498964.953, "dur": 88.883, + "args": { + "External id": 1427804,"Sequence number": 15348756, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850498965.969, "dur": 31.173, + "args": { + "External id": 1427805,"Sequence number": 15348756, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850498966.923, "dur": 29.616, + "args": { + "External id": 1427806,"Sequence number": 15348756, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14242 + } + }, + { + "ph": "s", "id": 126, "pid": 2338706, "tid": 2338706, "ts": 6413850498966.923, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850498998.790, "dur": 49.544, + "args": { + "External id": 1427807,"Sequence number": 15348757, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14243 + } + }, + { + "ph": "s", "id": 125, "pid": 2338706, "tid": 2338706, "ts": 6413850498998.790, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499051.034, "dur": 2.001, + "args": { + "External id": 1427808,"Sequence number": 15348758, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14244 + } + }, + { + "ph": "s", "id": 124, "pid": 2338706, "tid": 2338706, "ts": 6413850499051.034, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850499115.738, "dur": 6.683, + "args": { + "External id": 1427809,"Sequence number": 15348759, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499117.728, "dur": 4.422, + "args": { + "External id": 1427810,"Sequence number": 15348759, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14246 + } + }, + { + "ph": "s", "id": 123, "pid": 2338706, "tid": 2338706, "ts": 6413850499117.728, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850499134.041, "dur": 4.786, + "args": { + "External id": 1427811,"Sequence number": 15348760, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499135.148, "dur": 3.509, + "args": { + "External id": 1427812,"Sequence number": 15348760, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14248 + } + }, + { + "ph": "s", "id": 122, "pid": 2338706, "tid": 2338706, "ts": 6413850499135.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850499144.230, "dur": 3.180, + "args": { + "External id": 1427813,"Sequence number": 15348761, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499145.487, "dur": 1.780, + "args": { + "External id": 1427814,"Sequence number": 15348761, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14250 + } + }, + { + "ph": "s", "id": 121, "pid": 2338706, "tid": 2338706, "ts": 6413850499145.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850499184.168, "dur": 193.664, + "args": { + "External id": 1427815,"Sequence number": 15348762, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14251 + } + }, + { + "ph": "s", "id": 120, "pid": 2338706, "tid": 2338706, "ts": 6413850499184.168, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850499207.671, "dur": 11.757, + "args": { + "External id": 1427816,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850499211.847, "dur": 7.027, + "args": { + "External id": 1427817,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850499392.821, "dur": 120.802, + "args": { + "External id": 1427818,"Sequence number": 15348763, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14254 + } + }, + { + "ph": "s", "id": 119, "pid": 2338706, "tid": 2338706, "ts": 6413850499392.821, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850499407.738, "dur": 7.952, + "args": { + "External id": 1427819,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850499410.895, "dur": 4.231, + "args": { + "External id": 1427820,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413850499550.138, "dur": 204.170, + "args": { + "External id": 1427821,"Sequence number": 15348764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14257 + } + }, + { + "ph": "s", "id": 118, "pid": 2338706, "tid": 2338706, "ts": 6413850499550.138, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850499585.513, "dur": 137.994, + "args": { + "External id": 1427822,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850499636.610, "dur": 10.595, + "args": { + "External id": 1427823,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850499640.167, "dur": 6.221, + "args": { + "External id": 1427824,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850499650.604, "dur": 4.452, + "args": { + "External id": 1427825,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850499656.828, "dur": 2.086, + "args": { + "External id": 1427826,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850499661.762, "dur": 3.927, + "args": { + "External id": 1427827,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413850499736.843, "dur": 4.678, + "args": { + "External id": 1427828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850499760.482, "dur": 5.454, + "args": { + "External id": 1427829,"Sequence number": 15348765, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499762.079, "dur": 3.688, + "args": { + "External id": 1427830,"Sequence number": 15348765, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14266 + } + }, + { + "ph": "s", "id": 117, "pid": 2338706, "tid": 2338706, "ts": 6413850499762.079, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850499780.200, "dur": 123.652, + "args": { + "External id": 1427831,"Sequence number": 15348766, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850499781.480, "dur": 10.923, + "args": { + "External id": 1427832,"Sequence number": 15348766, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14268 + } + }, + { + "ph": "s", "id": 116, "pid": 2338706, "tid": 2338706, "ts": 6413850499781.480, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850499785.064, "dur": 5.774, + "args": { + "External id": 1427833,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850499788.427, "dur": 2.097, + "args": { + "External id": 1427834,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850499796.089, "dur": 107.404, + "args": { + "External id": 1427835,"Sequence number": 15348767, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850499798.616, "dur": 3.412, + "args": { + "External id": 1427836,"Sequence number": 15348767, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499799.723, "dur": 2.165, + "args": { + "External id": 1427837,"Sequence number": 15348767, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14273 + } + }, + { + "ph": "s", "id": 115, "pid": 2338706, "tid": 2338706, "ts": 6413850499799.723, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850499803.258, "dur": 88.152, + "args": { + "External id": 1427838,"Sequence number": 15348768, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14274 + } + }, + { + "ph": "s", "id": 114, "pid": 2338706, "tid": 2338706, "ts": 6413850499803.258, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499894.344, "dur": 8.225, + "args": { + "External id": 1427839,"Sequence number": 15348769, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14275 + } + }, + { + "ph": "s", "id": 113, "pid": 2338706, "tid": 2338706, "ts": 6413850499894.344, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850499952.558, "dur": 327.739, + "args": { + "External id": 1427840,"Sequence number": 15348770, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14276 + } + }, + { + "ph": "s", "id": 112, "pid": 2338706, "tid": 2338706, "ts": 6413850499952.558, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850499972.027, "dur": 26.878, + "args": { + "External id": 1427841,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850499973.198, "dur": 25.107, + "args": { + "External id": 1427842,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850500005.173, "dur": 6.821, + "args": { + "External id": 1427843,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500009.178, "dur": 2.660, + "args": { + "External id": 1427844,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500010.398, "dur": 1.305, + "args": { + "External id": 1427845,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850500020.837, "dur": 9.997, + "args": { + "External id": 1427846,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850500023.716, "dur": 6.652, + "args": { + "External id": 1427847,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850500038.579, "dur": 3.776, + "args": { + "External id": 1427848,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850500046.914, "dur": 5.593, + "args": { + "External id": 1427849,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500251.631, "dur": 5.103, + "args": { + "External id": 1427850,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500252.876, "dur": 3.478, + "args": { + "External id": 1427851,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500260.039, "dur": 2.834, + "args": { + "External id": 1427852,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500261.359, "dur": 1.396, + "args": { + "External id": 1427853,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850500301.581, "dur": 134.544, + "args": { + "External id": 1427854,"Sequence number": 15348771, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850500303.048, "dur": 12.779, + "args": { + "External id": 1427855,"Sequence number": 15348771, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14291 + } + }, + { + "ph": "s", "id": 111, "pid": 2338706, "tid": 2338706, "ts": 6413850500303.048, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850500306.381, "dur": 7.687, + "args": { + "External id": 1427856,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850500311.621, "dur": 2.089, + "args": { + "External id": 1427857,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850500316.860, "dur": 118.877, + "args": { + "External id": 1427858,"Sequence number": 15348772, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500319.158, "dur": 6.881, + "args": { + "External id": 1427859,"Sequence number": 15348772, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500320.158, "dur": 5.721, + "args": { + "External id": 1427860,"Sequence number": 15348772, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14296 + } + }, + { + "ph": "s", "id": 110, "pid": 2338706, "tid": 2338706, "ts": 6413850500320.158, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850500329.128, "dur": 99.555, + "args": { + "External id": 1427861,"Sequence number": 15348773, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14297 + } + }, + { + "ph": "s", "id": 109, "pid": 2338706, "tid": 2338706, "ts": 6413850500329.128, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500432.002, "dur": 3.057, + "args": { + "External id": 1427862,"Sequence number": 15348774, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14298 + } + }, + { + "ph": "s", "id": 108, "pid": 2338706, "tid": 2338706, "ts": 6413850500432.002, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850500445.339, "dur": 139.657, + "args": { + "External id": 1427863,"Sequence number": 15348775, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850500446.062, "dur": 57.989, + "args": { + "External id": 1427864,"Sequence number": 15348775, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14300 + } + }, + { + "ph": "s", "id": 107, "pid": 2338706, "tid": 2338706, "ts": 6413850500446.062, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850500494.938, "dur": 7.604, + "args": { + "External id": 1427865,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850500501.064, "dur": 1.208, + "args": { + "External id": 1427866,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850500504.941, "dur": 79.723, + "args": { + "External id": 1427867,"Sequence number": 15348776, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500506.312, "dur": 6.967, + "args": { + "External id": 1427868,"Sequence number": 15348776, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500507.342, "dur": 5.751, + "args": { + "External id": 1427869,"Sequence number": 15348776, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14305 + } + }, + { + "ph": "s", "id": 106, "pid": 2338706, "tid": 2338706, "ts": 6413850500507.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850500514.093, "dur": 60.714, + "args": { + "External id": 1427870,"Sequence number": 15348777, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14306 + } + }, + { + "ph": "s", "id": 105, "pid": 2338706, "tid": 2338706, "ts": 6413850500514.093, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500577.214, "dur": 6.947, + "args": { + "External id": 1427871,"Sequence number": 15348778, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14307 + } + }, + { + "ph": "s", "id": 104, "pid": 2338706, "tid": 2338706, "ts": 6413850500577.214, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850500609.958, "dur": 177.448, + "args": { + "External id": 1427872,"Sequence number": 15348779, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14308 + } + }, + { + "ph": "s", "id": 103, "pid": 2338706, "tid": 2338706, "ts": 6413850500609.958, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850500655.006, "dur": 6.088, + "args": { + "External id": 1427873,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850500703.497, "dur": 69.218, + "args": { + "External id": 1427874,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850500704.419, "dur": 6.566, + "args": { + "External id": 1427875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850500706.068, "dur": 3.909, + "args": { + "External id": 1427876,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850500708.460, "dur": 1.194, + "args": { + "External id": 1427877,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850500711.903, "dur": 60.463, + "args": { + "External id": 1427878,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500713.455, "dur": 3.050, + "args": { + "External id": 1427879,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500714.646, "dur": 1.665, + "args": { + "External id": 1427880,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850500717.361, "dur": 50.649, + "args": { + "External id": 1427881,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500770.156, "dur": 1.367, + "args": { + "External id": 1427882,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413850500797.357, "dur": 29.563, + "args": { + "External id": 1427883,"Sequence number": 15348780, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14319 + } + }, + { + "ph": "s", "id": 102, "pid": 2338706, "tid": 2338706, "ts": 6413850500797.357, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850500869.637, "dur": 289.907, + "args": { + "External id": 1427884,"Sequence number": 15348781, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14320 + } + }, + { + "ph": "s", "id": 101, "pid": 2338706, "tid": 2338706, "ts": 6413850500869.637, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850500891.721, "dur": 3.343, + "args": { + "External id": 1427885,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850500892.959, "dur": 1.897, + "args": { + "External id": 1427886,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850500904.496, "dur": 8.638, + "args": { + "External id": 1427887,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850500907.572, "dur": 5.101, + "args": { + "External id": 1427888,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850500920.029, "dur": 6.117, + "args": { + "External id": 1427889,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501138.079, "dur": 5.608, + "args": { + "External id": 1427890,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501139.795, "dur": 3.649, + "args": { + "External id": 1427891,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850501182.193, "dur": 110.135, + "args": { + "External id": 1427892,"Sequence number": 15348782, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850501183.460, "dur": 9.542, + "args": { + "External id": 1427893,"Sequence number": 15348782, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14329 + } + }, + { + "ph": "s", "id": 100, "pid": 2338706, "tid": 2338706, "ts": 6413850501183.460, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850501186.488, "dur": 4.961, + "args": { + "External id": 1427894,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850501189.412, "dur": 1.615, + "args": { + "External id": 1427895,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850501196.213, "dur": 95.854, + "args": { + "External id": 1427896,"Sequence number": 15348783, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501198.820, "dur": 4.221, + "args": { + "External id": 1427897,"Sequence number": 15348783, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501199.968, "dur": 2.901, + "args": { + "External id": 1427898,"Sequence number": 15348783, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14334 + } + }, + { + "ph": "s", "id": 99, "pid": 2338706, "tid": 2338706, "ts": 6413850501199.968, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850501204.092, "dur": 78.907, + "args": { + "External id": 1427899,"Sequence number": 15348784, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14335 + } + }, + { + "ph": "s", "id": 98, "pid": 2338706, "tid": 2338706, "ts": 6413850501204.092, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501286.344, "dur": 4.862, + "args": { + "External id": 1427900,"Sequence number": 15348785, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14336 + } + }, + { + "ph": "s", "id": 97, "pid": 2338706, "tid": 2338706, "ts": 6413850501286.344, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850501301.290, "dur": 68.676, + "args": { + "External id": 1427901,"Sequence number": 15348786, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850501302.033, "dur": 6.683, + "args": { + "External id": 1427902,"Sequence number": 15348786, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14338 + } + }, + { + "ph": "s", "id": 96, "pid": 2338706, "tid": 2338706, "ts": 6413850501302.033, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850501303.870, "dur": 3.414, + "args": { + "External id": 1427903,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850501306.141, "dur": 0.976, + "args": { + "External id": 1427904,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850501309.479, "dur": 60.194, + "args": { + "External id": 1427905,"Sequence number": 15348787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501313.044, "dur": 3.768, + "args": { + "External id": 1427906,"Sequence number": 15348787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501314.383, "dur": 2.295, + "args": { + "External id": 1427907,"Sequence number": 15348787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14343 + } + }, + { + "ph": "s", "id": 95, "pid": 2338706, "tid": 2338706, "ts": 6413850501314.383, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850501317.744, "dur": 46.807, + "args": { + "External id": 1427908,"Sequence number": 15348788, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14344 + } + }, + { + "ph": "s", "id": 94, "pid": 2338706, "tid": 2338706, "ts": 6413850501317.744, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501366.846, "dur": 2.393, + "args": { + "External id": 1427909,"Sequence number": 15348789, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14345 + } + }, + { + "ph": "s", "id": 93, "pid": 2338706, "tid": 2338706, "ts": 6413850501366.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850501377.678, "dur": 70.445, + "args": { + "External id": 1427910,"Sequence number": 15348790, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850501381.026, "dur": 8.592, + "args": { + "External id": 1427911,"Sequence number": 15348790, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14347 + } + }, + { + "ph": "s", "id": 92, "pid": 2338706, "tid": 2338706, "ts": 6413850501381.026, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850501382.847, "dur": 5.509, + "args": { + "External id": 1427912,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850501385.368, "dur": 2.744, + "args": { + "External id": 1427913,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850501390.474, "dur": 57.370, + "args": { + "External id": 1427914,"Sequence number": 15348791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501391.894, "dur": 7.445, + "args": { + "External id": 1427915,"Sequence number": 15348791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501395.529, "dur": 3.671, + "args": { + "External id": 1427916,"Sequence number": 15348791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14352 + } + }, + { + "ph": "s", "id": 91, "pid": 2338706, "tid": 2338706, "ts": 6413850501395.529, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850501400.237, "dur": 38.940, + "args": { + "External id": 1427917,"Sequence number": 15348792, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14353 + } + }, + { + "ph": "s", "id": 90, "pid": 2338706, "tid": 2338706, "ts": 6413850501400.237, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501441.374, "dur": 6.050, + "args": { + "External id": 1427918,"Sequence number": 15348793, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14354 + } + }, + { + "ph": "s", "id": 89, "pid": 2338706, "tid": 2338706, "ts": 6413850501441.374, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501466.455, "dur": 6.409, + "args": { + "External id": 1427919,"Sequence number": 15348794, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501470.241, "dur": 2.422, + "args": { + "External id": 1427920,"Sequence number": 15348794, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14356 + } + }, + { + "ph": "s", "id": 88, "pid": 2338706, "tid": 2338706, "ts": 6413850501470.241, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501481.164, "dur": 3.478, + "args": { + "External id": 1427921,"Sequence number": 15348795, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501482.728, "dur": 1.776, + "args": { + "External id": 1427922,"Sequence number": 15348795, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14358 + } + }, + { + "ph": "s", "id": 87, "pid": 2338706, "tid": 2338706, "ts": 6413850501482.728, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850501489.305, "dur": 5.859, + "args": { + "External id": 1427923,"Sequence number": 15348796, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850501490.524, "dur": 4.512, + "args": { + "External id": 1427924,"Sequence number": 15348796, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14360 + } + }, + { + "ph": "s", "id": 86, "pid": 2338706, "tid": 2338706, "ts": 6413850501490.524, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850501530.736, "dur": 165.609, + "args": { + "External id": 1427925,"Sequence number": 15348797, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14361 + } + }, + { + "ph": "s", "id": 85, "pid": 2338706, "tid": 2338706, "ts": 6413850501530.736, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850501550.855, "dur": 12.260, + "args": { + "External id": 1427926,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850501554.871, "dur": 7.854, + "args": { + "External id": 1427927,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850501710.867, "dur": 112.209, + "args": { + "External id": 1427928,"Sequence number": 15348798, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14364 + } + }, + { + "ph": "s", "id": 84, "pid": 2338706, "tid": 2338706, "ts": 6413850501710.867, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850501724.080, "dur": 7.457, + "args": { + "External id": 1427929,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850501726.772, "dur": 4.319, + "args": { + "External id": 1427930,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413850501855.169, "dur": 278.807, + "args": { + "External id": 1427931,"Sequence number": 15348799, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14367 + } + }, + { + "ph": "s", "id": 83, "pid": 2338706, "tid": 2338706, "ts": 6413850501855.169, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850501884.915, "dur": 210.228, + "args": { + "External id": 1427932,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850501936.366, "dur": 8.369, + "args": { + "External id": 1427933,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850501939.943, "dur": 4.320, + "args": { + "External id": 1427934,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850501948.157, "dur": 6.633, + "args": { + "External id": 1427935,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850501956.194, "dur": 1.682, + "args": { + "External id": 1427936,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850501963.065, "dur": 4.310, + "args": { + "External id": 1427937,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413850502113.475, "dur": 6.130, + "args": { + "External id": 1427938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502141.475, "dur": 6.528, + "args": { + "External id": 1427939,"Sequence number": 15348800, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502142.825, "dur": 5.040, + "args": { + "External id": 1427940,"Sequence number": 15348800, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14376 + } + }, + { + "ph": "s", "id": 82, "pid": 2338706, "tid": 2338706, "ts": 6413850502142.825, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850502163.391, "dur": 144.566, + "args": { + "External id": 1427941,"Sequence number": 15348801, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850502165.103, "dur": 15.115, + "args": { + "External id": 1427942,"Sequence number": 15348801, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14378 + } + }, + { + "ph": "s", "id": 81, "pid": 2338706, "tid": 2338706, "ts": 6413850502165.103, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850502170.394, "dur": 8.489, + "args": { + "External id": 1427943,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850502176.543, "dur": 2.049, + "args": { + "External id": 1427944,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850502181.736, "dur": 125.815, + "args": { + "External id": 1427945,"Sequence number": 15348802, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502184.387, "dur": 5.953, + "args": { + "External id": 1427946,"Sequence number": 15348802, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502185.540, "dur": 4.623, + "args": { + "External id": 1427947,"Sequence number": 15348802, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14383 + } + }, + { + "ph": "s", "id": 80, "pid": 2338706, "tid": 2338706, "ts": 6413850502185.540, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850502193.978, "dur": 102.951, + "args": { + "External id": 1427948,"Sequence number": 15348803, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14384 + } + }, + { + "ph": "s", "id": 79, "pid": 2338706, "tid": 2338706, "ts": 6413850502193.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502300.341, "dur": 6.353, + "args": { + "External id": 1427949,"Sequence number": 15348804, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14385 + } + }, + { + "ph": "s", "id": 78, "pid": 2338706, "tid": 2338706, "ts": 6413850502300.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850502347.736, "dur": 275.181, + "args": { + "External id": 1427950,"Sequence number": 15348805, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14386 + } + }, + { + "ph": "s", "id": 77, "pid": 2338706, "tid": 2338706, "ts": 6413850502347.736, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502371.918, "dur": 5.278, + "args": { + "External id": 1427951,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502375.293, "dur": 1.735, + "args": { + "External id": 1427952,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850502382.179, "dur": 3.540, + "args": { + "External id": 1427953,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502383.386, "dur": 2.207, + "args": { + "External id": 1427954,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502384.423, "dur": 1.053, + "args": { + "External id": 1427955,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850502395.360, "dur": 21.265, + "args": { + "External id": 1427956,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850502408.135, "dur": 8.144, + "args": { + "External id": 1427957,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850502427.478, "dur": 3.665, + "args": { + "External id": 1427958,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850502436.072, "dur": 4.743, + "args": { + "External id": 1427959,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502599.242, "dur": 3.808, + "args": { + "External id": 1427960,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502600.706, "dur": 2.091, + "args": { + "External id": 1427961,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502606.257, "dur": 2.689, + "args": { + "External id": 1427962,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502607.517, "dur": 1.309, + "args": { + "External id": 1427963,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850502642.715, "dur": 197.992, + "args": { + "External id": 1427964,"Sequence number": 15348806, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850502644.086, "dur": 11.842, + "args": { + "External id": 1427965,"Sequence number": 15348806, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14401 + } + }, + { + "ph": "s", "id": 76, "pid": 2338706, "tid": 2338706, "ts": 6413850502644.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850502648.422, "dur": 6.189, + "args": { + "External id": 1427966,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850502651.110, "dur": 3.119, + "args": { + "External id": 1427967,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850502657.435, "dur": 182.816, + "args": { + "External id": 1427968,"Sequence number": 15348807, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502728.279, "dur": 16.746, + "args": { + "External id": 1427969,"Sequence number": 15348807, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502742.212, "dur": 2.577, + "args": { + "External id": 1427970,"Sequence number": 15348807, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14406 + } + }, + { + "ph": "s", "id": 75, "pid": 2338706, "tid": 2338706, "ts": 6413850502742.212, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850502746.215, "dur": 87.506, + "args": { + "External id": 1427971,"Sequence number": 15348808, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14407 + } + }, + { + "ph": "s", "id": 74, "pid": 2338706, "tid": 2338706, "ts": 6413850502746.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502836.672, "dur": 2.847, + "args": { + "External id": 1427972,"Sequence number": 15348809, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14408 + } + }, + { + "ph": "s", "id": 73, "pid": 2338706, "tid": 2338706, "ts": 6413850502836.672, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850502851.821, "dur": 82.876, + "args": { + "External id": 1427973,"Sequence number": 15348810, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850502852.381, "dur": 11.029, + "args": { + "External id": 1427974,"Sequence number": 15348810, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14410 + } + }, + { + "ph": "s", "id": 72, "pid": 2338706, "tid": 2338706, "ts": 6413850502852.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850502856.139, "dur": 5.932, + "args": { + "External id": 1427975,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850502858.475, "dur": 3.387, + "args": { + "External id": 1427976,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850502863.974, "dur": 70.418, + "args": { + "External id": 1427977,"Sequence number": 15348811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850502865.158, "dur": 8.099, + "args": { + "External id": 1427978,"Sequence number": 15348811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502866.203, "dur": 6.888, + "args": { + "External id": 1427979,"Sequence number": 15348811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14415 + } + }, + { + "ph": "s", "id": 71, "pid": 2338706, "tid": 2338706, "ts": 6413850502866.203, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850502873.890, "dur": 52.392, + "args": { + "External id": 1427980,"Sequence number": 15348812, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14416 + } + }, + { + "ph": "s", "id": 70, "pid": 2338706, "tid": 2338706, "ts": 6413850502873.890, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850502928.525, "dur": 5.131, + "args": { + "External id": 1427981,"Sequence number": 15348813, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14417 + } + }, + { + "ph": "s", "id": 69, "pid": 2338706, "tid": 2338706, "ts": 6413850502928.525, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850502958.400, "dur": 259.859, + "args": { + "External id": 1427982,"Sequence number": 15348814, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14418 + } + }, + { + "ph": "s", "id": 68, "pid": 2338706, "tid": 2338706, "ts": 6413850502958.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850503027.045, "dur": 7.033, + "args": { + "External id": 1427983,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850503114.395, "dur": 86.287, + "args": { + "External id": 1427984,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850503115.480, "dur": 8.275, + "args": { + "External id": 1427985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850503117.564, "dur": 4.773, + "args": { + "External id": 1427986,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850503120.266, "dur": 1.637, + "args": { + "External id": 1427987,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850503124.637, "dur": 75.761, + "args": { + "External id": 1427988,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503126.524, "dur": 5.398, + "args": { + "External id": 1427989,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503130.109, "dur": 1.697, + "args": { + "External id": 1427990,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850503133.004, "dur": 60.169, + "args": { + "External id": 1427991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503196.066, "dur": 3.532, + "args": { + "External id": 1427992,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413850503229.897, "dur": 31.680, + "args": { + "External id": 1427993,"Sequence number": 15348815, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14429 + } + }, + { + "ph": "s", "id": 67, "pid": 2338706, "tid": 2338706, "ts": 6413850503229.897, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850503305.694, "dur": 230.148, + "args": { + "External id": 1427994,"Sequence number": 15348816, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 14430 + } + }, + { + "ph": "s", "id": 66, "pid": 2338706, "tid": 2338706, "ts": 6413850503305.694, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503331.741, "dur": 3.621, + "args": { + "External id": 1427995,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503332.841, "dur": 2.267, + "args": { + "External id": 1427996,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850503345.268, "dur": 12.004, + "args": { + "External id": 1427997,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850503351.711, "dur": 4.995, + "args": { + "External id": 1427998,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850503364.633, "dur": 4.425, + "args": { + "External id": 1427999,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503518.539, "dur": 4.059, + "args": { + "External id": 1428000,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503519.883, "dur": 2.437, + "args": { + "External id": 1428001,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850503556.003, "dur": 107.345, + "args": { + "External id": 1428002,"Sequence number": 15348817, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850503556.986, "dur": 9.883, + "args": { + "External id": 1428003,"Sequence number": 15348817, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14439 + } + }, + { + "ph": "s", "id": 65, "pid": 2338706, "tid": 2338706, "ts": 6413850503556.986, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850503559.577, "dur": 5.900, + "args": { + "External id": 1428004,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850503563.836, "dur": 1.422, + "args": { + "External id": 1428005,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850503568.281, "dur": 94.774, + "args": { + "External id": 1428006,"Sequence number": 15348818, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503569.807, "dur": 4.270, + "args": { + "External id": 1428007,"Sequence number": 15348818, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503570.749, "dur": 3.150, + "args": { + "External id": 1428008,"Sequence number": 15348818, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14444 + } + }, + { + "ph": "s", "id": 64, "pid": 2338706, "tid": 2338706, "ts": 6413850503570.749, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850503583.187, "dur": 73.392, + "args": { + "External id": 1428009,"Sequence number": 15348819, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14445 + } + }, + { + "ph": "s", "id": 63, "pid": 2338706, "tid": 2338706, "ts": 6413850503583.187, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503659.630, "dur": 2.711, + "args": { + "External id": 1428010,"Sequence number": 15348820, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14446 + } + }, + { + "ph": "s", "id": 62, "pid": 2338706, "tid": 2338706, "ts": 6413850503659.630, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850503672.708, "dur": 71.098, + "args": { + "External id": 1428011,"Sequence number": 15348821, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850503673.463, "dur": 7.920, + "args": { + "External id": 1428012,"Sequence number": 15348821, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14448 + } + }, + { + "ph": "s", "id": 61, "pid": 2338706, "tid": 2338706, "ts": 6413850503673.463, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850503675.140, "dur": 5.100, + "args": { + "External id": 1428013,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850503679.242, "dur": 0.821, + "args": { + "External id": 1428014,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850503682.137, "dur": 61.451, + "args": { + "External id": 1428015,"Sequence number": 15348822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503683.431, "dur": 3.676, + "args": { + "External id": 1428016,"Sequence number": 15348822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503684.380, "dur": 2.590, + "args": { + "External id": 1428017,"Sequence number": 15348822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14453 + } + }, + { + "ph": "s", "id": 60, "pid": 2338706, "tid": 2338706, "ts": 6413850503684.380, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850503687.741, "dur": 49.501, + "args": { + "External id": 1428018,"Sequence number": 15348823, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14454 + } + }, + { + "ph": "s", "id": 59, "pid": 2338706, "tid": 2338706, "ts": 6413850503687.741, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503739.503, "dur": 3.442, + "args": { + "External id": 1428019,"Sequence number": 15348824, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14455 + } + }, + { + "ph": "s", "id": 58, "pid": 2338706, "tid": 2338706, "ts": 6413850503739.503, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850503750.816, "dur": 63.879, + "args": { + "External id": 1428020,"Sequence number": 15348825, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 14456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850503751.379, "dur": 6.475, + "args": { + "External id": 1428021,"Sequence number": 15348825, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 14457 + } + }, + { + "ph": "s", "id": 57, "pid": 2338706, "tid": 2338706, "ts": 6413850503751.379, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850503752.851, "dur": 3.699, + "args": { + "External id": 1428022,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 14458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850503754.498, "dur": 1.820, + "args": { + "External id": 1428023,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 14459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850503758.541, "dur": 55.875, + "args": { + "External id": 1428024,"Sequence number": 15348826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 14460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503761.546, "dur": 4.897, + "args": { + "External id": 1428025,"Sequence number": 15348826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503762.571, "dur": 3.662, + "args": { + "External id": 1428026,"Sequence number": 15348826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14462 + } + }, + { + "ph": "s", "id": 56, "pid": 2338706, "tid": 2338706, "ts": 6413850503762.571, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850503767.178, "dur": 41.150, + "args": { + "External id": 1428027,"Sequence number": 15348827, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 14463 + } + }, + { + "ph": "s", "id": 55, "pid": 2338706, "tid": 2338706, "ts": 6413850503767.178, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503810.451, "dur": 3.598, + "args": { + "External id": 1428028,"Sequence number": 15348828, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 14464 + } + }, + { + "ph": "s", "id": 54, "pid": 2338706, "tid": 2338706, "ts": 6413850503810.451, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503835.049, "dur": 4.063, + "args": { + "External id": 1428029,"Sequence number": 15348829, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503836.249, "dur": 2.683, + "args": { + "External id": 1428030,"Sequence number": 15348829, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14466 + } + }, + { + "ph": "s", "id": 53, "pid": 2338706, "tid": 2338706, "ts": 6413850503836.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503847.209, "dur": 5.329, + "args": { + "External id": 1428031,"Sequence number": 15348830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503848.635, "dur": 3.758, + "args": { + "External id": 1428032,"Sequence number": 15348830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14468 + } + }, + { + "ph": "s", "id": 52, "pid": 2338706, "tid": 2338706, "ts": 6413850503848.635, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850503858.114, "dur": 5.684, + "args": { + "External id": 1428033,"Sequence number": 15348831, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850503861.483, "dur": 2.170, + "args": { + "External id": 1428034,"Sequence number": 15348831, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 14470 + } + }, + { + "ph": "s", "id": 51, "pid": 2338706, "tid": 2338706, "ts": 6413850503861.483, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850503896.262, "dur": 259.950, + "args": { + "External id": 1428035,"Sequence number": 15348832, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14471 + } + }, + { + "ph": "s", "id": 50, "pid": 2338706, "tid": 2338706, "ts": 6413850503896.262, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850503916.143, "dur": 10.740, + "args": { + "External id": 1428036,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850503919.958, "dur": 6.448, + "args": { + "External id": 1428037,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850504182.780, "dur": 155.528, + "args": { + "External id": 1428038,"Sequence number": 15348833, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 14474 + } + }, + { + "ph": "s", "id": 49, "pid": 2338706, "tid": 2338706, "ts": 6413850504182.780, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850504206.298, "dur": 12.574, + "args": { + "External id": 1428039,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 14475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850504210.317, "dur": 7.952, + "args": { + "External id": 1428040,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413850504374.878, "dur": 204.526, + "args": { + "External id": 1428041,"Sequence number": 15348834, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 14477 + } + }, + { + "ph": "s", "id": 48, "pid": 2338706, "tid": 2338706, "ts": 6413850504374.878, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850504404.624, "dur": 144.504, + "args": { + "External id": 1428042,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 14478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850504464.641, "dur": 9.286, + "args": { + "External id": 1428043,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 14479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850504468.378, "dur": 4.973, + "args": { + "External id": 1428044,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850504477.367, "dur": 5.025, + "args": { + "External id": 1428045,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850504483.890, "dur": 1.537, + "args": { + "External id": 1428046,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850504488.645, "dur": 3.776, + "args": { + "External id": 1428047,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413850504562.604, "dur": 6.260, + "args": { + "External id": 1428048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 14484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850504586.217, "dur": 7.610, + "args": { + "External id": 1428049,"Sequence number": 15348835, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850504588.216, "dur": 5.427, + "args": { + "External id": 1428050,"Sequence number": 15348835, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 14486 + } + }, + { + "ph": "s", "id": 47, "pid": 2338706, "tid": 2338706, "ts": 6413850504588.216, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850504608.222, "dur": 134.267, + "args": { + "External id": 1428051,"Sequence number": 15348836, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 14487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850504609.477, "dur": 12.342, + "args": { + "External id": 1428052,"Sequence number": 15348836, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 14488 + } + }, + { + "ph": "s", "id": 46, "pid": 2338706, "tid": 2338706, "ts": 6413850504609.477, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850504614.978, "dur": 5.475, + "args": { + "External id": 1428053,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 14489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850504618.119, "dur": 1.970, + "args": { + "External id": 1428054,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 14490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850504623.677, "dur": 118.450, + "args": { + "External id": 1428055,"Sequence number": 15348837, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 14491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850504626.219, "dur": 5.265, + "args": { + "External id": 1428056,"Sequence number": 15348837, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850504627.409, "dur": 3.964, + "args": { + "External id": 1428057,"Sequence number": 15348837, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14493 + } + }, + { + "ph": "s", "id": 45, "pid": 2338706, "tid": 2338706, "ts": 6413850504627.409, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850504632.709, "dur": 100.664, + "args": { + "External id": 1428058,"Sequence number": 15348838, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 14494 + } + }, + { + "ph": "s", "id": 44, "pid": 2338706, "tid": 2338706, "ts": 6413850504632.709, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850504736.816, "dur": 4.525, + "args": { + "External id": 1428059,"Sequence number": 15348839, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14495 + } + }, + { + "ph": "s", "id": 43, "pid": 2338706, "tid": 2338706, "ts": 6413850504736.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850504781.341, "dur": 333.535, + "args": { + "External id": 1428060,"Sequence number": 15348840, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 14496 + } + }, + { + "ph": "s", "id": 42, "pid": 2338706, "tid": 2338706, "ts": 6413850504781.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850504805.414, "dur": 8.085, + "args": { + "External id": 1428061,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850504808.881, "dur": 4.354, + "args": { + "External id": 1428062,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413850504817.819, "dur": 4.245, + "args": { + "External id": 1428063,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 14499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850504819.522, "dur": 2.419, + "args": { + "External id": 1428064,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850504820.620, "dur": 1.225, + "args": { + "External id": 1428065,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850504830.699, "dur": 7.656, + "args": { + "External id": 1428066,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850504833.330, "dur": 4.684, + "args": { + "External id": 1428067,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850504848.054, "dur": 3.183, + "args": { + "External id": 1428068,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850504855.667, "dur": 3.996, + "args": { + "External id": 1428069,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850505040.049, "dur": 5.426, + "args": { + "External id": 1428070,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505041.638, "dur": 3.439, + "args": { + "External id": 1428071,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850505049.104, "dur": 2.933, + "args": { + "External id": 1428072,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505050.610, "dur": 1.327, + "args": { + "External id": 1428073,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850505139.848, "dur": 127.304, + "args": { + "External id": 1428074,"Sequence number": 15348841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850505141.193, "dur": 10.969, + "args": { + "External id": 1428075,"Sequence number": 15348841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14511 + } + }, + { + "ph": "s", "id": 41, "pid": 2338706, "tid": 2338706, "ts": 6413850505141.193, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850505144.712, "dur": 5.812, + "args": { + "External id": 1428076,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850505148.264, "dur": 1.919, + "args": { + "External id": 1428077,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850505153.657, "dur": 113.146, + "args": { + "External id": 1428078,"Sequence number": 15348842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850505155.634, "dur": 6.298, + "args": { + "External id": 1428079,"Sequence number": 15348842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505158.749, "dur": 2.984, + "args": { + "External id": 1428080,"Sequence number": 15348842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14516 + } + }, + { + "ph": "s", "id": 40, "pid": 2338706, "tid": 2338706, "ts": 6413850505158.749, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850505163.337, "dur": 95.842, + "args": { + "External id": 1428081,"Sequence number": 15348843, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14517 + } + }, + { + "ph": "s", "id": 39, "pid": 2338706, "tid": 2338706, "ts": 6413850505163.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505262.974, "dur": 2.993, + "args": { + "External id": 1428082,"Sequence number": 15348844, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14518 + } + }, + { + "ph": "s", "id": 38, "pid": 2338706, "tid": 2338706, "ts": 6413850505262.974, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850505276.961, "dur": 82.963, + "args": { + "External id": 1428083,"Sequence number": 15348845, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 14519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850505277.922, "dur": 12.307, + "args": { + "External id": 1428084,"Sequence number": 15348845, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 14520 + } + }, + { + "ph": "s", "id": 37, "pid": 2338706, "tid": 2338706, "ts": 6413850505277.922, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850505283.382, "dur": 5.216, + "args": { + "External id": 1428085,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 14521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850505286.070, "dur": 2.279, + "args": { + "External id": 1428086,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 14522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850505290.964, "dur": 68.705, + "args": { + "External id": 1428087,"Sequence number": 15348846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 14523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850505291.879, "dur": 7.890, + "args": { + "External id": 1428088,"Sequence number": 15348846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505295.318, "dur": 4.307, + "args": { + "External id": 1428089,"Sequence number": 15348846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14525 + } + }, + { + "ph": "s", "id": 36, "pid": 2338706, "tid": 2338706, "ts": 6413850505295.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850505300.458, "dur": 52.912, + "args": { + "External id": 1428090,"Sequence number": 15348847, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 14526 + } + }, + { + "ph": "s", "id": 35, "pid": 2338706, "tid": 2338706, "ts": 6413850505300.458, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505355.919, "dur": 3.194, + "args": { + "External id": 1428091,"Sequence number": 15348848, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 14527 + } + }, + { + "ph": "s", "id": 34, "pid": 2338706, "tid": 2338706, "ts": 6413850505355.919, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850505385.189, "dur": 172.451, + "args": { + "External id": 1428092,"Sequence number": 15348849, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14528 + } + }, + { + "ph": "s", "id": 33, "pid": 2338706, "tid": 2338706, "ts": 6413850505385.189, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850505431.768, "dur": 6.263, + "args": { + "External id": 1428093,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850505472.376, "dur": 70.454, + "args": { + "External id": 1428094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 14530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850505473.214, "dur": 5.665, + "args": { + "External id": 1428095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 14531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850505474.555, "dur": 3.273, + "args": { + "External id": 1428096,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 14532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850505476.722, "dur": 0.751, + "args": { + "External id": 1428097,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 14533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850505479.827, "dur": 62.688, + "args": { + "External id": 1428098,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 14534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413850505481.677, "dur": 6.244, + "args": { + "External id": 1428099,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505484.565, "dur": 3.160, + "args": { + "External id": 1428100,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 14536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850505488.826, "dur": 49.315, + "args": { + "External id": 1428101,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 14537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505540.700, "dur": 1.127, + "args": { + "External id": 1428102,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413850505567.981, "dur": 27.855, + "args": { + "External id": 1428103,"Sequence number": 15348850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 14539 + } + }, + { + "ph": "s", "id": 32, "pid": 2338706, "tid": 2338706, "ts": 6413850505567.981, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338706, "tid": 2338706, + "ts": 6413850505617.361, "dur": 48.738, + "args": { + "External id": 1428104,"Sequence number": 15348851, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 14540 + } + }, + { + "ph": "s", "id": 31, "pid": 2338706, "tid": 2338706, "ts": 6413850505617.361, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338706, "tid": 2338706, + "ts": 6413850505629.585, "dur": 31.323, + "args": { + "External id": 1428105,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 14541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850505663.025, "dur": 1.203, + "args": { + "External id": 1428106,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 16384], []], "Ev Idx": 14542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413850505705.711, "dur": 50.280, + "args": { + "External id": 1428107,"Record function id": 0, "Ev Idx": 14543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338706, "tid": 2338706, + "ts": 6413850505758.204, "dur": 245.357, + "args": { + "External id": 1428108,"Record function id": 0, "Ev Idx": 14544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850505799.778, "dur": 171.547, + "args": { + "External id": 1428109,"Sequence number": 15348852, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [67108864, 16384, 4096, 1]], "Input Dims": [[4096], [8, 4096, 4, 4096]], "Ev Idx": 14545 + } + }, + { + "ph": "s", "id": 30, "pid": 2338706, "tid": 2338706, "ts": 6413850505799.778, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413850505880.504, "dur": 45.516, + "args": { + "External id": 1428110,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [131072, 4096], [4096], [131072], [], [], [], [], [], [], [], [], []], "Ev Idx": 14546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850506157.695, "dur": 49.051, + "args": { + "External id": 1428111,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850506161.486, "dur": 7.440, + "args": { + "External id": 1428112,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506172.234, "dur": 34.172, + "args": { + "External id": 1428113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 14549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506175.889, "dur": 29.937, + "args": { + "External id": 1428114,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 14550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850506212.739, "dur": 22.833, + "args": { + "External id": 1428115,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850506214.067, "dur": 3.334, + "args": { + "External id": 1428116,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506220.273, "dur": 15.020, + "args": { + "External id": 1428117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 14553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506220.880, "dur": 14.037, + "args": { + "External id": 1428118,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 14554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850506239.199, "dur": 20.881, + "args": { + "External id": 1428119,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850506240.139, "dur": 4.272, + "args": { + "External id": 1428120,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506245.266, "dur": 14.535, + "args": { + "External id": 1428121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 14557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506246.238, "dur": 13.182, + "args": { + "External id": 1428122,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 14558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850506272.657, "dur": 0.764, + "args": { + "External id": 1428123,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 14559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338706, "tid": 2338706, + "ts": 6413850506282.929, "dur": 14.881, + "args": { + "External id": 1428124,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "5", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 14560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506292.947, "dur": 2.455, + "args": { + "External id": 1428125,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 14561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506305.858, "dur": 8.937, + "args": { + "External id": 1428126,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 14562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506311.821, "dur": 1.042, + "args": { + "External id": 1428127,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 14563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506316.515, "dur": 6.428, + "args": { + "External id": 1428128,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 14564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506319.106, "dur": 2.962, + "args": { + "External id": 1428129,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 14565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506324.702, "dur": 3.914, + "args": { + "External id": 1428130,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 14566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506327.441, "dur": 0.549, + "args": { + "External id": 1428131,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 14567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506332.470, "dur": 3.504, + "args": { + "External id": 1428132,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 14568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506334.832, "dur": 0.491, + "args": { + "External id": 1428133,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 14569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506337.563, "dur": 3.787, + "args": { + "External id": 1428134,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 14570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506339.921, "dur": 0.620, + "args": { + "External id": 1428135,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 14571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506342.581, "dur": 4.075, + "args": { + "External id": 1428136,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4096, 4], [], [], [], []], "Ev Idx": 14572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506345.357, "dur": 0.668, + "args": { + "External id": 1428137,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 14573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850506350.989, "dur": 6.546, + "args": { + "External id": 1428138,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4096, 4], [], []], "Ev Idx": 14574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506356.053, "dur": 0.537, + "args": { + "External id": 1428139,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 14575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506362.801, "dur": 3.498, + "args": { + "External id": 1428140,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 14576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506365.069, "dur": 0.536, + "args": { + "External id": 1428141,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 14577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850506371.577, "dur": 12.078, + "args": { + "External id": 1428142,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 14578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506381.436, "dur": 0.661, + "args": { + "External id": 1428143,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 14579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506384.984, "dur": 5.138, + "args": { + "External id": 1428144,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 14580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506386.514, "dur": 2.925, + "args": { + "External id": 1428145,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 14581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506393.115, "dur": 7.493, + "args": { + "External id": 1428146,"Sequence number": 15348853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 14582 + } + }, + { + "ph": "s", "id": 29, "pid": 2338706, "tid": 2338706, "ts": 6413850506393.115, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506397.795, "dur": 0.827, + "args": { + "External id": 1428147,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 14583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506404.086, "dur": 4.924, + "args": { + "External id": 1428148,"Sequence number": 15348854, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 14584 + } + }, + { + "ph": "s", "id": 28, "pid": 2338706, "tid": 2338706, "ts": 6413850506404.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506407.606, "dur": 0.482, + "args": { + "External id": 1428149,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 14585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850506410.208, "dur": 5.527, + "args": { + "External id": 1428150,"Sequence number": 15348855, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 14586 + } + }, + { + "ph": "s", "id": 27, "pid": 2338706, "tid": 2338706, "ts": 6413850506410.208, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506414.176, "dur": 0.554, + "args": { + "External id": 1428151,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 14587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850506416.770, "dur": 5.040, + "args": { + "External id": 1428152,"Sequence number": 15348856, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 14588 + } + }, + { + "ph": "s", "id": 26, "pid": 2338706, "tid": 2338706, "ts": 6413850506416.770, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506419.862, "dur": 1.068, + "args": { + "External id": 1428153,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 14589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850506426.915, "dur": 45.332, + "args": { + "External id": 1428154,"Sequence number": 15348857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 14590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850506432.108, "dur": 39.899, + "args": { + "External id": 1428155,"Sequence number": 15348857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 14591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850506435.189, "dur": 8.141, + "args": { + "External id": 1428156,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 14592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850506437.755, "dur": 4.954, + "args": { + "External id": 1428157,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506445.233, "dur": 26.038, + "args": { + "External id": 1428158,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 14594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850506501.170, "dur": 6.596, + "args": { + "External id": 1428159,"Sequence number": 15348857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 14595 + } + }, + { + "ph": "s", "id": 25, "pid": 2338706, "tid": 2338706, "ts": 6413850506501.170, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850506510.898, "dur": 1.378, + "args": { + "External id": 1428160,"Sequence number": 15348858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 14596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850506544.512, "dur": 126770.099, + "args": { + "External id": 1428161,"Sequence number": 15348858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 14597 + } + }, + { + "ph": "s", "id": 24, "pid": 2338706, "tid": 2338706, "ts": 6413850506544.512, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850506562.476, "dur": 34.414, + "args": { + "External id": 1428162,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850506563.093, "dur": 33.536, + "args": { + "External id": 1428163,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850506564.726, "dur": 8.400, + "args": { + "External id": 1428164,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850506566.215, "dur": 6.407, + "args": { + "External id": 1428165,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506574.288, "dur": 21.970, + "args": { + "External id": 1428166,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 14602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850506617.076, "dur": 29.385, + "args": { + "External id": 1428167,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850506618.885, "dur": 6.967, + "args": { + "External id": 1428168,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 14604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506621.329, "dur": 4.196, + "args": { + "External id": 1428169,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506626.781, "dur": 19.427, + "args": { + "External id": 1428170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 14606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506628.013, "dur": 17.793, + "args": { + "External id": 1428171,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 14607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850506650.142, "dur": 24.582, + "args": { + "External id": 1428172,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 14608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850506651.153, "dur": 7.340, + "args": { + "External id": 1428173,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 14609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506654.401, "dur": 3.777, + "args": { + "External id": 1428174,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506659.402, "dur": 15.104, + "args": { + "External id": 1428175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506660.082, "dur": 13.974, + "args": { + "External id": 1428176,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 14612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850506679.651, "dur": 21.337, + "args": { + "External id": 1428177,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 14613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850506682.823, "dur": 2.973, + "args": { + "External id": 1428178,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506686.476, "dur": 14.226, + "args": { + "External id": 1428179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 14615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506687.374, "dur": 12.817, + "args": { + "External id": 1428180,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413850506712.249, "dur": 32.324, + "args": { + "External id": 1428181,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850506749.573, "dur": 87.069, + "args": { + "External id": 1428182,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850506753.874, "dur": 82.244, + "args": { + "External id": 1428183,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506761.296, "dur": 1.335, + "args": { + "External id": 1428184,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 14620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850506764.442, "dur": 47.623, + "args": { + "External id": 1428185,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850506766.299, "dur": 45.420, + "args": { + "External id": 1428186,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 14622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850506785.733, "dur": 4.484, + "args": { + "External id": 1428187,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850506791.402, "dur": 19.845, + "args": { + "External id": 1428188,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 14624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413850506844.571, "dur": 119160.792, + "args": { + "External id": 1428189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 14625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413850506846.353, "dur": 119154.060, + "args": { + "External id": 1428190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 14626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850626038.904, "dur": 58.397, + "args": { + "External id": 1428191,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850626049.781, "dur": 42.664, + "args": { + "External id": 1428192,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850626106.874, "dur": 164.309, + "args": { + "External id": 1428193,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850626109.224, "dur": 11.062, + "args": { + "External id": 1428194,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850626113.065, "dur": 5.792, + "args": { + "External id": 1428195,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850626116.819, "dur": 1.682, + "args": { + "External id": 1428196,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850626122.144, "dur": 148.066, + "args": { + "External id": 1428197,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850626129.492, "dur": 139.321, + "args": { + "External id": 1428198,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850626281.093, "dur": 6.248, + "args": { + "External id": 1428199,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850626284.522, "dur": 0.744, + "args": { + "External id": 1428200,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850626302.416, "dur": 5.102, + "args": { + "External id": 1428201,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850626322.982, "dur": 11.664, + "args": { + "External id": 1428202,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850626326.343, "dur": 7.943, + "args": { + "External id": 1428203,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850626524.192, "dur": 314.683, + "args": { + "External id": 1428204,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850626530.790, "dur": 3.026, + "args": { + "External id": 1428205,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850626537.463, "dur": 300.511, + "args": { + "External id": 1428206,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850626541.336, "dur": 0.990, + "args": { + "External id": 1428207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850626546.057, "dur": 40.202, + "args": { + "External id": 1428208,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850626589.266, "dur": 7.539, + "args": { + "External id": 1428209,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850626595.121, "dur": 1.188, + "args": { + "External id": 1428210,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850626599.253, "dur": 37.120, + "args": { + "External id": 1428211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850626601.227, "dur": 2.166, + "args": { + "External id": 1428212,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850626606.139, "dur": 29.827, + "args": { + "External id": 1428213,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850626614.557, "dur": 3.629, + "args": { + "External id": 1428214,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850626642.726, "dur": 36.035, + "args": { + "External id": 1428215,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850626682.613, "dur": 25.308, + "args": { + "External id": 1428216,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850626712.966, "dur": 21.893, + "args": { + "External id": 1428217,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850626738.059, "dur": 22.422, + "args": { + "External id": 1428218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850626763.382, "dur": 32.576, + "args": { + "External id": 1428219,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850626766.710, "dur": 1.914, + "args": { + "External id": 1428220,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850626773.418, "dur": 0.756, + "args": { + "External id": 1428221,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850626799.136, "dur": 20.525, + "args": { + "External id": 1428222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850626821.544, "dur": 14.999, + "args": { + "External id": 1428223,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850626847.491, "dur": 2.621, + "args": { + "External id": 1428224,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850626859.483, "dur": 6.334, + "args": { + "External id": 1428225,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850626863.666, "dur": 0.729, + "args": { + "External id": 1428226,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850626993.422, "dur": 139.055, + "args": { + "External id": 1428227,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850627144.163, "dur": 13.003, + "args": { + "External id": 1428228,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627152.767, "dur": 1.140, + "args": { + "External id": 1428229,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627159.374, "dur": 39.659, + "args": { + "External id": 1428230,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850627207.720, "dur": 8.801, + "args": { + "External id": 1428231,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850627211.091, "dur": 4.491, + "args": { + "External id": 1428232,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627213.454, "dur": 1.737, + "args": { + "External id": 1428233,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850627221.943, "dur": 71.960, + "args": { + "External id": 1428234,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850627226.111, "dur": 66.738, + "args": { + "External id": 1428235,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627300.793, "dur": 21.701, + "args": { + "External id": 1428236,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850627330.898, "dur": 7.338, + "args": { + "External id": 1428237,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627333.612, "dur": 3.459, + "args": { + "External id": 1428238,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850627344.127, "dur": 58.220, + "args": { + "External id": 1428239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850627345.668, "dur": 6.740, + "args": { + "External id": 1428240,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850627347.006, "dur": 4.710, + "args": { + "External id": 1428241,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627351.053, "dur": 0.485, + "args": { + "External id": 1428242,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850627353.331, "dur": 48.561, + "args": { + "External id": 1428243,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850627354.062, "dur": 47.088, + "args": { + "External id": 1428244,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850627407.689, "dur": 6.124, + "args": { + "External id": 1428245,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627410.020, "dur": 2.276, + "args": { + "External id": 1428246,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850627422.431, "dur": 2.456, + "args": { + "External id": 1428247,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850627437.577, "dur": 8.256, + "args": { + "External id": 1428248,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850627440.093, "dur": 5.407, + "args": { + "External id": 1428249,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850627571.996, "dur": 215.136, + "args": { + "External id": 1428250,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850627575.702, "dur": 2.619, + "args": { + "External id": 1428251,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850627580.285, "dur": 206.349, + "args": { + "External id": 1428252,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850627581.747, "dur": 0.451, + "args": { + "External id": 1428253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850627583.840, "dur": 28.032, + "args": { + "External id": 1428254,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850627616.307, "dur": 4.134, + "args": { + "External id": 1428255,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627619.360, "dur": 0.726, + "args": { + "External id": 1428256,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850627621.605, "dur": 30.456, + "args": { + "External id": 1428257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850627623.101, "dur": 4.646, + "args": { + "External id": 1428258,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850627629.350, "dur": 22.155, + "args": { + "External id": 1428259,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627634.809, "dur": 3.046, + "args": { + "External id": 1428260,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850627654.068, "dur": 22.774, + "args": { + "External id": 1428261,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627679.167, "dur": 15.015, + "args": { + "External id": 1428262,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850627698.128, "dur": 15.668, + "args": { + "External id": 1428263,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627715.505, "dur": 14.077, + "args": { + "External id": 1428264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850627731.922, "dur": 25.638, + "args": { + "External id": 1428265,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627736.528, "dur": 2.883, + "args": { + "External id": 1428266,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627741.477, "dur": 0.752, + "args": { + "External id": 1428267,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627759.211, "dur": 13.191, + "args": { + "External id": 1428268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850627773.707, "dur": 11.782, + "args": { + "External id": 1428269,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850627794.669, "dur": 2.626, + "args": { + "External id": 1428270,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850627808.149, "dur": 5.834, + "args": { + "External id": 1428271,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627811.170, "dur": 0.609, + "args": { + "External id": 1428272,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850627901.166, "dur": 64.614, + "args": { + "External id": 1428273,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850627971.957, "dur": 28.217, + "args": { + "External id": 1428274,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850627995.131, "dur": 2.335, + "args": { + "External id": 1428275,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628002.090, "dur": 35.088, + "args": { + "External id": 1428276,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850628043.631, "dur": 45.808, + "args": { + "External id": 1428277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850628045.479, "dur": 5.993, + "args": { + "External id": 1428278,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628050.254, "dur": 1.018, + "args": { + "External id": 1428279,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850628096.139, "dur": 66.354, + "args": { + "External id": 1428280,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850628097.510, "dur": 64.000, + "args": { + "External id": 1428281,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628168.139, "dur": 22.364, + "args": { + "External id": 1428282,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850628198.612, "dur": 5.300, + "args": { + "External id": 1428283,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628201.802, "dur": 0.950, + "args": { + "External id": 1428284,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850628209.238, "dur": 88.154, + "args": { + "External id": 1428285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850628212.559, "dur": 9.447, + "args": { + "External id": 1428286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850628213.877, "dur": 7.360, + "args": { + "External id": 1428287,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628217.920, "dur": 3.156, + "args": { + "External id": 1428288,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850628223.119, "dur": 73.672, + "args": { + "External id": 1428289,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850628224.076, "dur": 72.016, + "args": { + "External id": 1428290,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850628304.217, "dur": 4.724, + "args": { + "External id": 1428291,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628307.090, "dur": 0.424, + "args": { + "External id": 1428292,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850628319.530, "dur": 2.160, + "args": { + "External id": 1428293,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850628331.559, "dur": 7.400, + "args": { + "External id": 1428294,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850628333.827, "dur": 4.782, + "args": { + "External id": 1428295,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850628454.882, "dur": 214.008, + "args": { + "External id": 1428296,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850628457.891, "dur": 2.266, + "args": { + "External id": 1428297,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850628461.868, "dur": 206.462, + "args": { + "External id": 1428298,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850628467.324, "dur": 0.625, + "args": { + "External id": 1428299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850628469.453, "dur": 25.206, + "args": { + "External id": 1428300,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850628496.635, "dur": 3.351, + "args": { + "External id": 1428301,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628498.869, "dur": 0.805, + "args": { + "External id": 1428302,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850628501.336, "dur": 26.711, + "args": { + "External id": 1428303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850628504.098, "dur": 1.648, + "args": { + "External id": 1428304,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850628507.197, "dur": 20.393, + "args": { + "External id": 1428305,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628510.422, "dur": 3.100, + "args": { + "External id": 1428306,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850628529.703, "dur": 25.395, + "args": { + "External id": 1428307,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628556.980, "dur": 17.034, + "args": { + "External id": 1428308,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850628579.839, "dur": 15.402, + "args": { + "External id": 1428309,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628597.100, "dur": 15.949, + "args": { + "External id": 1428310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850628615.097, "dur": 23.435, + "args": { + "External id": 1428311,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628617.428, "dur": 1.669, + "args": { + "External id": 1428312,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628621.450, "dur": 0.712, + "args": { + "External id": 1428313,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628640.277, "dur": 12.951, + "args": { + "External id": 1428314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628656.640, "dur": 10.308, + "args": { + "External id": 1428315,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850628676.403, "dur": 1.908, + "args": { + "External id": 1428316,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850628688.324, "dur": 4.237, + "args": { + "External id": 1428317,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628691.076, "dur": 0.496, + "args": { + "External id": 1428318,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850628770.115, "dur": 59.077, + "args": { + "External id": 1428319,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850628835.038, "dur": 6.920, + "args": { + "External id": 1428320,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628838.522, "dur": 1.963, + "args": { + "External id": 1428321,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628844.353, "dur": 28.296, + "args": { + "External id": 1428322,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850628881.005, "dur": 6.139, + "args": { + "External id": 1428323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850628882.758, "dur": 3.734, + "args": { + "External id": 1428324,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628885.435, "dur": 0.795, + "args": { + "External id": 1428325,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850628889.953, "dur": 44.877, + "args": { + "External id": 1428326,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850628891.295, "dur": 42.798, + "args": { + "External id": 1428327,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850628939.228, "dur": 15.660, + "args": { + "External id": 1428328,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850628961.355, "dur": 6.989, + "args": { + "External id": 1428329,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628966.326, "dur": 0.995, + "args": { + "External id": 1428330,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850628972.784, "dur": 120.114, + "args": { + "External id": 1428331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850628992.211, "dur": 6.589, + "args": { + "External id": 1428332,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850628994.493, "dur": 3.505, + "args": { + "External id": 1428333,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850628996.600, "dur": 1.028, + "args": { + "External id": 1428334,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850628999.897, "dur": 92.310, + "args": { + "External id": 1428335,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850629003.267, "dur": 87.465, + "args": { + "External id": 1428336,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850629102.235, "dur": 6.213, + "args": { + "External id": 1428337,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629105.638, "dur": 1.203, + "args": { + "External id": 1428338,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850629117.384, "dur": 2.203, + "args": { + "External id": 1428339,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629129.165, "dur": 8.988, + "args": { + "External id": 1428340,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629132.011, "dur": 5.790, + "args": { + "External id": 1428341,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850629249.311, "dur": 215.154, + "args": { + "External id": 1428342,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629251.914, "dur": 4.531, + "args": { + "External id": 1428343,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850629258.116, "dur": 205.820, + "args": { + "External id": 1428344,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850629259.736, "dur": 0.433, + "args": { + "External id": 1428345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850629261.654, "dur": 23.955, + "args": { + "External id": 1428346,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850629287.413, "dur": 5.031, + "args": { + "External id": 1428347,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629291.354, "dur": 0.866, + "args": { + "External id": 1428348,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850629293.449, "dur": 25.169, + "args": { + "External id": 1428349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629294.539, "dur": 1.515, + "args": { + "External id": 1428350,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850629300.099, "dur": 18.124, + "args": { + "External id": 1428351,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629303.130, "dur": 2.635, + "args": { + "External id": 1428352,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850629320.403, "dur": 24.864, + "args": { + "External id": 1428353,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629347.158, "dur": 15.292, + "args": { + "External id": 1428354,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850629365.614, "dur": 16.563, + "args": { + "External id": 1428355,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629383.830, "dur": 15.859, + "args": { + "External id": 1428356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850629401.698, "dur": 26.194, + "args": { + "External id": 1428357,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629406.064, "dur": 1.916, + "args": { + "External id": 1428358,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629410.156, "dur": 0.748, + "args": { + "External id": 1428359,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629432.080, "dur": 14.997, + "args": { + "External id": 1428360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629448.535, "dur": 14.314, + "args": { + "External id": 1428361,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850629471.497, "dur": 2.048, + "args": { + "External id": 1428362,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850629483.718, "dur": 4.312, + "args": { + "External id": 1428363,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629486.412, "dur": 0.642, + "args": { + "External id": 1428364,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850629565.803, "dur": 65.001, + "args": { + "External id": 1428365,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850629637.161, "dur": 5.194, + "args": { + "External id": 1428366,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629640.366, "dur": 0.767, + "args": { + "External id": 1428367,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629646.539, "dur": 28.807, + "args": { + "External id": 1428368,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850629680.521, "dur": 7.139, + "args": { + "External id": 1428369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850629682.472, "dur": 4.368, + "args": { + "External id": 1428370,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629684.716, "dur": 1.937, + "args": { + "External id": 1428371,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850629690.641, "dur": 46.824, + "args": { + "External id": 1428372,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850629691.843, "dur": 44.968, + "args": { + "External id": 1428373,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850629742.013, "dur": 15.823, + "args": { + "External id": 1428374,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850629766.735, "dur": 4.597, + "args": { + "External id": 1428375,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629769.333, "dur": 1.012, + "args": { + "External id": 1428376,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850629776.265, "dur": 59.213, + "args": { + "External id": 1428377,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850629777.542, "dur": 4.241, + "args": { + "External id": 1428378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850629778.614, "dur": 2.553, + "args": { + "External id": 1428379,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629780.347, "dur": 0.667, + "args": { + "External id": 1428380,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850629785.107, "dur": 49.820, + "args": { + "External id": 1428381,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850629786.075, "dur": 48.217, + "args": { + "External id": 1428382,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850629840.197, "dur": 4.262, + "args": { + "External id": 1428383,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850629842.367, "dur": 0.762, + "args": { + "External id": 1428384,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850629850.819, "dur": 1.799, + "args": { + "External id": 1428385,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629861.080, "dur": 8.799, + "args": { + "External id": 1428386,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629865.489, "dur": 4.096, + "args": { + "External id": 1428387,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850629966.604, "dur": 319.976, + "args": { + "External id": 1428388,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850629970.949, "dur": 2.400, + "args": { + "External id": 1428389,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850629995.129, "dur": 290.539, + "args": { + "External id": 1428390,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850629996.558, "dur": 0.645, + "args": { + "External id": 1428391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850629998.730, "dur": 26.692, + "args": { + "External id": 1428392,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850630027.332, "dur": 5.035, + "args": { + "External id": 1428393,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630031.059, "dur": 1.007, + "args": { + "External id": 1428394,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850630033.490, "dur": 74.210, + "args": { + "External id": 1428395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850630036.945, "dur": 1.996, + "args": { + "External id": 1428396,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850630040.297, "dur": 66.251, + "args": { + "External id": 1428397,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630043.484, "dur": 3.096, + "args": { + "External id": 1428398,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850630110.744, "dur": 40.870, + "args": { + "External id": 1428399,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630154.333, "dur": 22.657, + "args": { + "External id": 1428400,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850630181.427, "dur": 19.224, + "args": { + "External id": 1428401,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630202.667, "dur": 16.292, + "args": { + "External id": 1428402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850630221.575, "dur": 30.282, + "args": { + "External id": 1428403,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630224.809, "dur": 2.401, + "args": { + "External id": 1428404,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630231.851, "dur": 0.986, + "args": { + "External id": 1428405,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630253.879, "dur": 15.329, + "args": { + "External id": 1428406,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630270.807, "dur": 13.416, + "args": { + "External id": 1428407,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850630299.440, "dur": 3.582, + "args": { + "External id": 1428408,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850630316.401, "dur": 4.958, + "args": { + "External id": 1428409,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630319.652, "dur": 0.688, + "args": { + "External id": 1428410,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850630423.147, "dur": 81.073, + "args": { + "External id": 1428411,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850630513.358, "dur": 5.036, + "args": { + "External id": 1428412,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630516.254, "dur": 0.757, + "args": { + "External id": 1428413,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630520.223, "dur": 28.944, + "args": { + "External id": 1428414,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850630555.309, "dur": 8.258, + "args": { + "External id": 1428415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850630558.061, "dur": 4.739, + "args": { + "External id": 1428416,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630560.720, "dur": 1.802, + "args": { + "External id": 1428417,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850630569.014, "dur": 49.067, + "args": { + "External id": 1428418,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850630570.454, "dur": 46.743, + "args": { + "External id": 1428419,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630623.032, "dur": 16.610, + "args": { + "External id": 1428420,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850630646.993, "dur": 4.731, + "args": { + "External id": 1428421,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630649.639, "dur": 0.856, + "args": { + "External id": 1428422,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850630657.008, "dur": 53.714, + "args": { + "External id": 1428423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850630658.329, "dur": 6.409, + "args": { + "External id": 1428424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850630661.289, "dur": 2.686, + "args": { + "External id": 1428425,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630662.991, "dur": 0.811, + "args": { + "External id": 1428426,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850630665.589, "dur": 44.711, + "args": { + "External id": 1428427,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850630666.501, "dur": 43.021, + "args": { + "External id": 1428428,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850630715.559, "dur": 5.383, + "args": { + "External id": 1428429,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630717.786, "dur": 1.635, + "args": { + "External id": 1428430,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850630727.987, "dur": 1.968, + "args": { + "External id": 1428431,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850630766.552, "dur": 8.124, + "args": { + "External id": 1428432,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850630769.152, "dur": 5.235, + "args": { + "External id": 1428433,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850630880.873, "dur": 282.384, + "args": { + "External id": 1428434,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850630883.337, "dur": 2.441, + "args": { + "External id": 1428435,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850630888.636, "dur": 274.020, + "args": { + "External id": 1428436,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850630890.540, "dur": 0.430, + "args": { + "External id": 1428437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850630894.890, "dur": 22.880, + "args": { + "External id": 1428438,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850630919.592, "dur": 5.405, + "args": { + "External id": 1428439,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850630921.867, "dur": 2.750, + "args": { + "External id": 1428440,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850630926.162, "dur": 22.312, + "args": { + "External id": 1428441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850630927.374, "dur": 1.571, + "args": { + "External id": 1428442,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850630930.271, "dur": 17.870, + "args": { + "External id": 1428443,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630933.346, "dur": 2.592, + "args": { + "External id": 1428444,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850630949.972, "dur": 46.368, + "args": { + "External id": 1428445,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850630999.438, "dur": 17.022, + "args": { + "External id": 1428446,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850631019.780, "dur": 16.151, + "args": { + "External id": 1428447,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631037.748, "dur": 13.632, + "args": { + "External id": 1428448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850631096.243, "dur": 32.348, + "args": { + "External id": 1428449,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631103.225, "dur": 3.058, + "args": { + "External id": 1428450,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631109.065, "dur": 1.017, + "args": { + "External id": 1428451,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631130.411, "dur": 15.548, + "args": { + "External id": 1428452,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631147.030, "dur": 14.315, + "args": { + "External id": 1428453,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850631172.940, "dur": 3.096, + "args": { + "External id": 1428454,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850631187.125, "dur": 4.803, + "args": { + "External id": 1428455,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631190.259, "dur": 0.639, + "args": { + "External id": 1428456,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850631280.631, "dur": 73.231, + "args": { + "External id": 1428457,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850631360.392, "dur": 5.804, + "args": { + "External id": 1428458,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631363.791, "dur": 0.877, + "args": { + "External id": 1428459,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631368.062, "dur": 33.988, + "args": { + "External id": 1428460,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850631407.198, "dur": 9.606, + "args": { + "External id": 1428461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850631409.067, "dur": 6.844, + "args": { + "External id": 1428462,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631414.243, "dur": 1.459, + "args": { + "External id": 1428463,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850631420.148, "dur": 48.194, + "args": { + "External id": 1428464,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850631421.515, "dur": 46.079, + "args": { + "External id": 1428465,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631473.140, "dur": 17.041, + "args": { + "External id": 1428466,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850631496.926, "dur": 4.099, + "args": { + "External id": 1428467,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631499.323, "dur": 0.639, + "args": { + "External id": 1428468,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850631505.702, "dur": 55.823, + "args": { + "External id": 1428469,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850631508.909, "dur": 4.291, + "args": { + "External id": 1428470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850631509.802, "dur": 2.779, + "args": { + "External id": 1428471,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631511.700, "dur": 0.726, + "args": { + "External id": 1428472,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850631513.969, "dur": 47.127, + "args": { + "External id": 1428473,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850631514.423, "dur": 45.980, + "args": { + "External id": 1428474,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850631566.338, "dur": 4.344, + "args": { + "External id": 1428475,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631568.657, "dur": 0.689, + "args": { + "External id": 1428476,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850631579.276, "dur": 1.546, + "args": { + "External id": 1428477,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850631589.700, "dur": 6.939, + "args": { + "External id": 1428478,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850631592.063, "dur": 4.233, + "args": { + "External id": 1428479,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850631693.978, "dur": 343.796, + "args": { + "External id": 1428480,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850631788.824, "dur": 5.013, + "args": { + "External id": 1428481,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850631795.578, "dur": 241.528, + "args": { + "External id": 1428482,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850631799.699, "dur": 0.497, + "args": { + "External id": 1428483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850631801.706, "dur": 27.057, + "args": { + "External id": 1428484,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850631830.565, "dur": 4.871, + "args": { + "External id": 1428485,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631834.233, "dur": 0.925, + "args": { + "External id": 1428486,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850631836.595, "dur": 25.663, + "args": { + "External id": 1428487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850631837.803, "dur": 1.830, + "args": { + "External id": 1428488,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850631840.924, "dur": 21.008, + "args": { + "External id": 1428489,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631843.976, "dur": 3.072, + "args": { + "External id": 1428490,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850631863.812, "dur": 26.677, + "args": { + "External id": 1428491,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631892.257, "dur": 20.713, + "args": { + "External id": 1428492,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850631918.525, "dur": 16.934, + "args": { + "External id": 1428493,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631936.836, "dur": 14.791, + "args": { + "External id": 1428494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850631953.932, "dur": 45.332, + "args": { + "External id": 1428495,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850631955.785, "dur": 1.400, + "args": { + "External id": 1428496,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850631959.374, "dur": 0.560, + "args": { + "External id": 1428497,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632002.270, "dur": 17.571, + "args": { + "External id": 1428498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632023.556, "dur": 12.140, + "args": { + "External id": 1428499,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850632048.192, "dur": 3.258, + "args": { + "External id": 1428500,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850632100.198, "dur": 6.723, + "args": { + "External id": 1428501,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632104.818, "dur": 0.638, + "args": { + "External id": 1428502,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850632198.453, "dur": 74.121, + "args": { + "External id": 1428503,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850632279.105, "dur": 5.586, + "args": { + "External id": 1428504,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632282.072, "dur": 0.817, + "args": { + "External id": 1428505,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632286.621, "dur": 29.426, + "args": { + "External id": 1428506,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850632324.388, "dur": 6.083, + "args": { + "External id": 1428507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850632326.150, "dur": 3.514, + "args": { + "External id": 1428508,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632328.026, "dur": 1.383, + "args": { + "External id": 1428509,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850632333.898, "dur": 48.207, + "args": { + "External id": 1428510,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850632335.264, "dur": 46.060, + "args": { + "External id": 1428511,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632386.610, "dur": 18.364, + "args": { + "External id": 1428512,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850632411.566, "dur": 6.421, + "args": { + "External id": 1428513,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632416.078, "dur": 0.770, + "args": { + "External id": 1428514,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850632422.832, "dur": 54.208, + "args": { + "External id": 1428515,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 14951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850632423.612, "dur": 3.785, + "args": { + "External id": 1428516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 14952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850632424.341, "dur": 2.411, + "args": { + "External id": 1428517,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 14953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632425.735, "dur": 0.853, + "args": { + "External id": 1428518,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 14954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850632428.048, "dur": 48.470, + "args": { + "External id": 1428519,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850632431.442, "dur": 44.358, + "args": { + "External id": 1428520,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 14956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850632481.763, "dur": 6.283, + "args": { + "External id": 1428521,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632483.832, "dur": 2.745, + "args": { + "External id": 1428522,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850632494.764, "dur": 1.882, + "args": { + "External id": 1428523,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 14959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850632505.557, "dur": 7.144, + "args": { + "External id": 1428524,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 14960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850632507.618, "dur": 4.776, + "args": { + "External id": 1428525,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850632611.497, "dur": 214.107, + "args": { + "External id": 1428526,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850632613.464, "dur": 2.444, + "args": { + "External id": 1428527,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850632617.820, "dur": 207.273, + "args": { + "External id": 1428528,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 14964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850632619.397, "dur": 0.450, + "args": { + "External id": 1428529,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850632621.154, "dur": 26.278, + "args": { + "External id": 1428530,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 14966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850632649.559, "dur": 3.109, + "args": { + "External id": 1428531,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 14967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632651.552, "dur": 0.708, + "args": { + "External id": 1428532,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 14968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850632653.625, "dur": 28.501, + "args": { + "External id": 1428533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850632654.839, "dur": 1.692, + "args": { + "External id": 1428534,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 14970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850632660.090, "dur": 21.552, + "args": { + "External id": 1428535,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 14971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632665.254, "dur": 2.665, + "args": { + "External id": 1428536,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850632683.639, "dur": 27.963, + "args": { + "External id": 1428537,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632713.593, "dur": 15.211, + "args": { + "External id": 1428538,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850632731.780, "dur": 15.761, + "args": { + "External id": 1428539,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 14975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632749.117, "dur": 15.417, + "args": { + "External id": 1428540,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 14976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850632766.813, "dur": 23.044, + "args": { + "External id": 1428541,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 14977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632769.239, "dur": 1.734, + "args": { + "External id": 1428542,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 14978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632772.930, "dur": 0.602, + "args": { + "External id": 1428543,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 14979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632794.467, "dur": 14.952, + "args": { + "External id": 1428544,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 14980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850632810.717, "dur": 13.038, + "args": { + "External id": 1428545,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 14981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850632832.737, "dur": 1.935, + "args": { + "External id": 1428546,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 14982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850632843.698, "dur": 4.097, + "args": { + "External id": 1428547,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 14983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850632846.225, "dur": 0.609, + "args": { + "External id": 1428548,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850632918.003, "dur": 54.470, + "args": { + "External id": 1428549,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 14985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850632999.109, "dur": 8.693, + "args": { + "External id": 1428550,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 14986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633004.309, "dur": 1.618, + "args": { + "External id": 1428551,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 14987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633011.959, "dur": 31.272, + "args": { + "External id": 1428552,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 14988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850633049.557, "dur": 5.663, + "args": { + "External id": 1428553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 14989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850633051.272, "dur": 3.223, + "args": { + "External id": 1428554,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 14990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633053.372, "dur": 0.897, + "args": { + "External id": 1428555,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 14991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850633096.937, "dur": 58.889, + "args": { + "External id": 1428556,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850633098.341, "dur": 56.475, + "args": { + "External id": 1428557,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 14993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633161.497, "dur": 18.822, + "args": { + "External id": 1428558,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 14994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850633189.207, "dur": 29.957, + "args": { + "External id": 1428559,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 14995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850633192.235, "dur": 26.501, + "args": { + "External id": 1428560,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 14996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633200.342, "dur": 0.754, + "args": { + "External id": 1428561,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 14997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850633226.693, "dur": 30.742, + "args": { + "External id": 1428562,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 14998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850633228.623, "dur": 28.575, + "args": { + "External id": 1428563,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 14999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633233.794, "dur": 4.285, + "args": { + "External id": 1428564,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633239.318, "dur": 17.290, + "args": { + "External id": 1428565,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850633273.723, "dur": 8.718, + "args": { + "External id": 1428566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850633278.733, "dur": 3.378, + "args": { + "External id": 1428567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850633283.745, "dur": 1.408, + "args": { + "External id": 1428568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850633284.409, "dur": 0.587, + "args": { + "External id": 1428569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633337.292, "dur": 26.138, + "args": { + "External id": 1428570,"Sequence number": 15348859, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15006 + } + }, + { + "ph": "s", "id": 23, "pid": 2338706, "tid": 2338706, "ts": 6413850633337.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850633370.736, "dur": 12.170, + "args": { + "External id": 1428571,"Sequence number": 15348860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 15007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633379.692, "dur": 1.390, + "args": { + "External id": 1428572,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850633385.841, "dur": 11.546, + "args": { + "External id": 1428573,"Sequence number": 15348860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "1"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 15009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633392.949, "dur": 3.014, + "args": { + "External id": 1428574,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850633398.750, "dur": 2.720, + "args": { + "External id": 1428575,"Sequence number": 15348860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 15011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633400.161, "dur": 0.614, + "args": { + "External id": 1428576,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 15012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850633406.667, "dur": 6.568, + "args": { + "External id": 1428577,"Sequence number": 15348860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15013 + } + }, + { + "ph": "s", "id": 22, "pid": 2338706, "tid": 2338706, "ts": 6413850633406.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633410.759, "dur": 0.758, + "args": { + "External id": 1428578,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850633416.487, "dur": 5.237, + "args": { + "External id": 1428579,"Sequence number": 15348861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15015 + } + }, + { + "ph": "s", "id": 21, "pid": 2338706, "tid": 2338706, "ts": 6413850633416.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633420.081, "dur": 0.573, + "args": { + "External id": 1428580,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850633422.853, "dur": 5.608, + "args": { + "External id": 1428581,"Sequence number": 15348862, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 15017 + } + }, + { + "ph": "s", "id": 20, "pid": 2338706, "tid": 2338706, "ts": 6413850633422.853, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633426.646, "dur": 0.794, + "args": { + "External id": 1428582,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850633429.753, "dur": 4.877, + "args": { + "External id": 1428583,"Sequence number": 15348863, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 15019 + } + }, + { + "ph": "s", "id": 19, "pid": 2338706, "tid": 2338706, "ts": 6413850633429.753, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633432.928, "dur": 0.787, + "args": { + "External id": 1428584,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 15020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850633438.733, "dur": 34.800, + "args": { + "External id": 1428585,"Sequence number": 15348864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850633442.980, "dur": 30.260, + "args": { + "External id": 1428586,"Sequence number": 15348864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850633446.088, "dur": 7.436, + "args": { + "External id": 1428587,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 15023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850633448.664, "dur": 4.249, + "args": { + "External id": 1428588,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633454.533, "dur": 18.205, + "args": { + "External id": 1428589,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 15025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850633503.204, "dur": 3.920, + "args": { + "External id": 1428590,"Sequence number": 15348864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 15026 + } + }, + { + "ph": "s", "id": 18, "pid": 2338706, "tid": 2338706, "ts": 6413850633503.204, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850633509.860, "dur": 3.434, + "args": { + "External id": 1428591,"Sequence number": 15348865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850633551.867, "dur": 44821.702, + "args": { + "External id": 1428592,"Sequence number": 15348865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 15028 + } + }, + { + "ph": "s", "id": 17, "pid": 2338706, "tid": 2338706, "ts": 6413850633551.867, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850633570.934, "dur": 28.784, + "args": { + "External id": 1428593,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850633571.774, "dur": 27.694, + "args": { + "External id": 1428594,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850633575.282, "dur": 5.220, + "args": { + "External id": 1428595,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850633576.710, "dur": 3.351, + "args": { + "External id": 1428596,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633581.587, "dur": 17.493, + "args": { + "External id": 1428597,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 15033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850633618.394, "dur": 30.791, + "args": { + "External id": 1428598,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850633619.634, "dur": 5.994, + "args": { + "External id": 1428599,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633621.650, "dur": 3.626, + "args": { + "External id": 1428600,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633627.134, "dur": 21.780, + "args": { + "External id": 1428601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633629.330, "dur": 19.044, + "args": { + "External id": 1428602,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850633652.845, "dur": 23.440, + "args": { + "External id": 1428603,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850633653.782, "dur": 7.014, + "args": { + "External id": 1428604,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633657.527, "dur": 2.991, + "args": { + "External id": 1428605,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633661.336, "dur": 14.718, + "args": { + "External id": 1428606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633661.763, "dur": 13.899, + "args": { + "External id": 1428607,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 15043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850633683.467, "dur": 20.616, + "args": { + "External id": 1428608,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 15044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850633685.223, "dur": 3.309, + "args": { + "External id": 1428609,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633689.266, "dur": 14.397, + "args": { + "External id": 1428610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 15046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633690.095, "dur": 13.128, + "args": { + "External id": 1428611,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413850633712.283, "dur": 22.648, + "args": { + "External id": 1428612,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850633738.045, "dur": 77.688, + "args": { + "External id": 1428613,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850633740.056, "dur": 75.178, + "args": { + "External id": 1428614,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633744.826, "dur": 1.432, + "args": { + "External id": 1428615,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850633747.561, "dur": 31.615, + "args": { + "External id": 1428616,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850633749.023, "dur": 29.856, + "args": { + "External id": 1428617,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 15053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850633751.462, "dur": 6.131, + "args": { + "External id": 1428618,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850633758.429, "dur": 20.080, + "args": { + "External id": 1428619,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 15055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413850633820.606, "dur": 37435.936, + "args": { + "External id": 1428620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413850633822.354, "dur": 37431.455, + "args": { + "External id": 1428621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850671277.834, "dur": 15.888, + "args": { + "External id": 1428622,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850671288.025, "dur": 2.973, + "args": { + "External id": 1428623,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850671301.346, "dur": 138.601, + "args": { + "External id": 1428624,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850671303.239, "dur": 10.039, + "args": { + "External id": 1428625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850671307.434, "dur": 4.848, + "args": { + "External id": 1428626,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850671309.889, "dur": 2.076, + "args": { + "External id": 1428627,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850671314.767, "dur": 124.308, + "args": { + "External id": 1428628,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850671319.130, "dur": 119.143, + "args": { + "External id": 1428629,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850671445.693, "dur": 6.194, + "args": { + "External id": 1428630,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850671449.273, "dur": 0.693, + "args": { + "External id": 1428631,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850671465.097, "dur": 4.601, + "args": { + "External id": 1428632,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850671483.072, "dur": 11.306, + "args": { + "External id": 1428633,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850671487.315, "dur": 6.725, + "args": { + "External id": 1428634,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850671679.704, "dur": 241.801, + "args": { + "External id": 1428635,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850671684.665, "dur": 2.835, + "args": { + "External id": 1428636,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850671689.305, "dur": 231.468, + "args": { + "External id": 1428637,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850671691.101, "dur": 0.525, + "args": { + "External id": 1428638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850671693.298, "dur": 37.604, + "args": { + "External id": 1428639,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850671733.133, "dur": 3.789, + "args": { + "External id": 1428640,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850671735.895, "dur": 0.675, + "args": { + "External id": 1428641,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850671738.103, "dur": 32.999, + "args": { + "External id": 1428642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850671739.274, "dur": 1.434, + "args": { + "External id": 1428643,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850671744.775, "dur": 25.803, + "args": { + "External id": 1428644,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850671750.884, "dur": 3.486, + "args": { + "External id": 1428645,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850671773.079, "dur": 28.014, + "args": { + "External id": 1428646,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850671803.482, "dur": 17.940, + "args": { + "External id": 1428647,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850671824.745, "dur": 17.832, + "args": { + "External id": 1428648,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850671844.478, "dur": 15.399, + "args": { + "External id": 1428649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850671862.202, "dur": 26.459, + "args": { + "External id": 1428650,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850671865.160, "dur": 1.658, + "args": { + "External id": 1428651,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850671871.608, "dur": 0.654, + "args": { + "External id": 1428652,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850671890.298, "dur": 14.825, + "args": { + "External id": 1428653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850671906.808, "dur": 12.760, + "args": { + "External id": 1428654,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850671930.375, "dur": 2.309, + "args": { + "External id": 1428655,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850671940.761, "dur": 5.749, + "args": { + "External id": 1428656,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850671944.438, "dur": 0.543, + "args": { + "External id": 1428657,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850672099.590, "dur": 107.104, + "args": { + "External id": 1428658,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850672218.409, "dur": 17.241, + "args": { + "External id": 1428659,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672226.812, "dur": 4.166, + "args": { + "External id": 1428660,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672237.597, "dur": 33.771, + "args": { + "External id": 1428661,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850672279.189, "dur": 8.539, + "args": { + "External id": 1428662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850672282.565, "dur": 4.297, + "args": { + "External id": 1428663,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672285.201, "dur": 1.309, + "args": { + "External id": 1428664,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850672291.755, "dur": 60.907, + "args": { + "External id": 1428665,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850672295.502, "dur": 56.191, + "args": { + "External id": 1428666,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672377.463, "dur": 23.150, + "args": { + "External id": 1428667,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850672408.973, "dur": 5.923, + "args": { + "External id": 1428668,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672412.988, "dur": 0.650, + "args": { + "External id": 1428669,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850672420.611, "dur": 60.132, + "args": { + "External id": 1428670,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850672421.695, "dur": 10.198, + "args": { + "External id": 1428671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850672426.340, "dur": 4.739, + "args": { + "External id": 1428672,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672427.867, "dur": 2.913, + "args": { + "External id": 1428673,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850672432.607, "dur": 47.646, + "args": { + "External id": 1428674,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850672433.340, "dur": 46.143, + "args": { + "External id": 1428675,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850672486.163, "dur": 4.284, + "args": { + "External id": 1428676,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672488.219, "dur": 0.733, + "args": { + "External id": 1428677,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850672499.954, "dur": 2.422, + "args": { + "External id": 1428678,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850672517.062, "dur": 9.600, + "args": { + "External id": 1428679,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850672521.141, "dur": 5.192, + "args": { + "External id": 1428680,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850672660.927, "dur": 236.793, + "args": { + "External id": 1428681,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850672665.819, "dur": 5.384, + "args": { + "External id": 1428682,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850672672.904, "dur": 224.181, + "args": { + "External id": 1428683,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850672674.676, "dur": 0.693, + "args": { + "External id": 1428684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850672681.809, "dur": 27.820, + "args": { + "External id": 1428685,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850672711.439, "dur": 4.277, + "args": { + "External id": 1428686,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672714.474, "dur": 0.968, + "args": { + "External id": 1428687,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850672716.885, "dur": 30.104, + "args": { + "External id": 1428688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850672718.483, "dur": 3.896, + "args": { + "External id": 1428689,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850672724.248, "dur": 22.430, + "args": { + "External id": 1428690,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672727.799, "dur": 3.381, + "args": { + "External id": 1428691,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850672748.840, "dur": 26.583, + "args": { + "External id": 1428692,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672777.450, "dur": 17.480, + "args": { + "External id": 1428693,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850672798.517, "dur": 17.872, + "args": { + "External id": 1428694,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672818.350, "dur": 16.552, + "args": { + "External id": 1428695,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850672839.675, "dur": 23.909, + "args": { + "External id": 1428696,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672842.260, "dur": 1.795, + "args": { + "External id": 1428697,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672846.479, "dur": 0.695, + "args": { + "External id": 1428698,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672865.093, "dur": 14.722, + "args": { + "External id": 1428699,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850672881.339, "dur": 14.213, + "args": { + "External id": 1428700,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850672905.028, "dur": 2.416, + "args": { + "External id": 1428701,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850672919.045, "dur": 5.726, + "args": { + "External id": 1428702,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850672921.798, "dur": 1.805, + "args": { + "External id": 1428703,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850673046.427, "dur": 131.038, + "args": { + "External id": 1428704,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850673187.257, "dur": 8.704, + "args": { + "External id": 1428705,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673190.980, "dur": 2.856, + "args": { + "External id": 1428706,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673197.760, "dur": 34.461, + "args": { + "External id": 1428707,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850673239.321, "dur": 12.053, + "args": { + "External id": 1428708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850673241.447, "dur": 8.870, + "args": { + "External id": 1428709,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673246.654, "dur": 3.318, + "args": { + "External id": 1428710,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850673255.087, "dur": 57.925, + "args": { + "External id": 1428711,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850673256.216, "dur": 56.079, + "args": { + "External id": 1428712,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673318.363, "dur": 21.263, + "args": { + "External id": 1428713,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850673347.501, "dur": 4.101, + "args": { + "External id": 1428714,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673349.791, "dur": 0.671, + "args": { + "External id": 1428715,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850673357.049, "dur": 86.335, + "args": { + "External id": 1428716,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850673360.533, "dur": 4.107, + "args": { + "External id": 1428717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850673361.667, "dur": 2.262, + "args": { + "External id": 1428718,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673363.045, "dur": 0.724, + "args": { + "External id": 1428719,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850673365.495, "dur": 77.377, + "args": { + "External id": 1428720,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850673366.435, "dur": 75.586, + "args": { + "External id": 1428721,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850673491.647, "dur": 6.309, + "args": { + "External id": 1428722,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673495.824, "dur": 0.626, + "args": { + "External id": 1428723,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850673509.196, "dur": 2.001, + "args": { + "External id": 1428724,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850673522.045, "dur": 9.644, + "args": { + "External id": 1428725,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850673524.626, "dur": 6.730, + "args": { + "External id": 1428726,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850673657.680, "dur": 226.477, + "args": { + "External id": 1428727,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850673660.290, "dur": 3.913, + "args": { + "External id": 1428728,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850673665.667, "dur": 217.913, + "args": { + "External id": 1428729,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850673669.970, "dur": 0.701, + "args": { + "External id": 1428730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850673672.059, "dur": 31.834, + "args": { + "External id": 1428731,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850673705.931, "dur": 3.291, + "args": { + "External id": 1428732,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673708.150, "dur": 0.727, + "args": { + "External id": 1428733,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850673710.346, "dur": 26.652, + "args": { + "External id": 1428734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850673711.607, "dur": 1.573, + "args": { + "External id": 1428735,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850673714.547, "dur": 22.016, + "args": { + "External id": 1428736,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673719.712, "dur": 3.033, + "args": { + "External id": 1428737,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850673738.545, "dur": 25.554, + "args": { + "External id": 1428738,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673765.983, "dur": 16.996, + "args": { + "External id": 1428739,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850673788.467, "dur": 16.265, + "args": { + "External id": 1428740,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673806.759, "dur": 16.182, + "args": { + "External id": 1428741,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850673825.151, "dur": 23.983, + "args": { + "External id": 1428742,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673827.885, "dur": 1.603, + "args": { + "External id": 1428743,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673831.758, "dur": 0.846, + "args": { + "External id": 1428744,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673850.583, "dur": 15.512, + "args": { + "External id": 1428745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850673869.747, "dur": 12.458, + "args": { + "External id": 1428746,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850673892.358, "dur": 1.927, + "args": { + "External id": 1428747,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850673904.637, "dur": 4.057, + "args": { + "External id": 1428748,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850673907.136, "dur": 0.511, + "args": { + "External id": 1428749,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850674012.241, "dur": 111.440, + "args": { + "External id": 1428750,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850674133.100, "dur": 6.609, + "args": { + "External id": 1428751,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674136.830, "dur": 0.986, + "args": { + "External id": 1428752,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674141.640, "dur": 33.171, + "args": { + "External id": 1428753,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850674183.329, "dur": 6.548, + "args": { + "External id": 1428754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850674185.129, "dur": 3.953, + "args": { + "External id": 1428755,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674186.929, "dur": 1.858, + "args": { + "External id": 1428756,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850674193.329, "dur": 54.605, + "args": { + "External id": 1428757,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850674194.784, "dur": 52.110, + "args": { + "External id": 1428758,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674253.088, "dur": 17.017, + "args": { + "External id": 1428759,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850674276.982, "dur": 6.997, + "args": { + "External id": 1428760,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674282.104, "dur": 0.853, + "args": { + "External id": 1428761,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850674288.913, "dur": 51.888, + "args": { + "External id": 1428762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850674290.111, "dur": 3.684, + "args": { + "External id": 1428763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850674290.897, "dur": 2.224, + "args": { + "External id": 1428764,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674292.073, "dur": 0.899, + "args": { + "External id": 1428765,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850674294.576, "dur": 45.726, + "args": { + "External id": 1428766,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850674297.579, "dur": 41.983, + "args": { + "External id": 1428767,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850674346.029, "dur": 6.195, + "args": { + "External id": 1428768,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674348.357, "dur": 2.483, + "args": { + "External id": 1428769,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850674359.928, "dur": 2.220, + "args": { + "External id": 1428770,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850674372.340, "dur": 7.398, + "args": { + "External id": 1428771,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850674374.583, "dur": 4.877, + "args": { + "External id": 1428772,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850674489.021, "dur": 200.592, + "args": { + "External id": 1428773,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850674491.474, "dur": 2.217, + "args": { + "External id": 1428774,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850674495.549, "dur": 193.629, + "args": { + "External id": 1428775,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850674497.139, "dur": 0.470, + "args": { + "External id": 1428776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850674498.965, "dur": 25.271, + "args": { + "External id": 1428777,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850674526.090, "dur": 5.446, + "args": { + "External id": 1428778,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674528.437, "dur": 2.814, + "args": { + "External id": 1428779,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850674532.611, "dur": 27.978, + "args": { + "External id": 1428780,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850674533.759, "dur": 1.767, + "args": { + "External id": 1428781,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850674539.174, "dur": 20.940, + "args": { + "External id": 1428782,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674544.580, "dur": 3.058, + "args": { + "External id": 1428783,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850674562.027, "dur": 21.592, + "args": { + "External id": 1428784,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674585.496, "dur": 14.850, + "args": { + "External id": 1428785,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850674603.424, "dur": 14.682, + "args": { + "External id": 1428786,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674619.840, "dur": 13.207, + "args": { + "External id": 1428787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850674635.193, "dur": 21.103, + "args": { + "External id": 1428788,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674637.506, "dur": 1.955, + "args": { + "External id": 1428789,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674641.239, "dur": 0.791, + "args": { + "External id": 1428790,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674660.571, "dur": 12.433, + "args": { + "External id": 1428791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674674.253, "dur": 13.756, + "args": { + "External id": 1428792,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850674697.245, "dur": 1.935, + "args": { + "External id": 1428793,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850674708.712, "dur": 3.877, + "args": { + "External id": 1428794,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674711.374, "dur": 0.331, + "args": { + "External id": 1428795,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850674785.612, "dur": 55.634, + "args": { + "External id": 1428796,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850674846.986, "dur": 5.139, + "args": { + "External id": 1428797,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674849.831, "dur": 1.140, + "args": { + "External id": 1428798,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674856.257, "dur": 27.172, + "args": { + "External id": 1428799,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850674888.342, "dur": 5.280, + "args": { + "External id": 1428800,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850674890.048, "dur": 2.882, + "args": { + "External id": 1428801,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850674892.064, "dur": 0.691, + "args": { + "External id": 1428802,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850674896.069, "dur": 49.667, + "args": { + "External id": 1428803,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850674897.065, "dur": 47.591, + "args": { + "External id": 1428804,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850674950.471, "dur": 17.384, + "args": { + "External id": 1428805,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850674999.103, "dur": 9.870, + "args": { + "External id": 1428806,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675003.709, "dur": 3.752, + "args": { + "External id": 1428807,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850675015.504, "dur": 104.150, + "args": { + "External id": 1428808,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850675016.987, "dur": 6.791, + "args": { + "External id": 1428809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850675018.670, "dur": 4.232, + "args": { + "External id": 1428810,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675022.095, "dur": 0.650, + "args": { + "External id": 1428811,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850675026.986, "dur": 92.025, + "args": { + "External id": 1428812,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850675027.651, "dur": 89.711, + "args": { + "External id": 1428813,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850675127.696, "dur": 5.500, + "args": { + "External id": 1428814,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675130.562, "dur": 0.991, + "args": { + "External id": 1428815,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850675140.700, "dur": 2.015, + "args": { + "External id": 1428816,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850675152.441, "dur": 10.463, + "args": { + "External id": 1428817,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850675157.329, "dur": 5.242, + "args": { + "External id": 1428818,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850675267.537, "dur": 211.214, + "args": { + "External id": 1428819,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850675270.591, "dur": 2.114, + "args": { + "External id": 1428820,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850675274.142, "dur": 204.147, + "args": { + "External id": 1428821,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850675277.869, "dur": 0.346, + "args": { + "External id": 1428822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850675279.635, "dur": 25.976, + "args": { + "External id": 1428823,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850675307.358, "dur": 3.577, + "args": { + "External id": 1428824,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675309.724, "dur": 0.895, + "args": { + "External id": 1428825,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850675311.857, "dur": 31.269, + "args": { + "External id": 1428826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850675316.976, "dur": 3.483, + "args": { + "External id": 1428827,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850675321.891, "dur": 20.835, + "args": { + "External id": 1428828,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675325.011, "dur": 3.199, + "args": { + "External id": 1428829,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850675344.675, "dur": 22.457, + "args": { + "External id": 1428830,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675369.016, "dur": 16.705, + "args": { + "External id": 1428831,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850675388.446, "dur": 15.536, + "args": { + "External id": 1428832,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675405.482, "dur": 15.632, + "args": { + "External id": 1428833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850675423.167, "dur": 24.309, + "args": { + "External id": 1428834,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675425.140, "dur": 1.342, + "args": { + "External id": 1428835,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675430.964, "dur": 0.836, + "args": { + "External id": 1428836,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675448.817, "dur": 14.705, + "args": { + "External id": 1428837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675464.809, "dur": 12.152, + "args": { + "External id": 1428838,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850675486.047, "dur": 1.555, + "args": { + "External id": 1428839,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850675497.066, "dur": 3.968, + "args": { + "External id": 1428840,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675499.559, "dur": 0.467, + "args": { + "External id": 1428841,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850675574.925, "dur": 60.674, + "args": { + "External id": 1428842,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850675643.793, "dur": 6.606, + "args": { + "External id": 1428843,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675646.484, "dur": 2.683, + "args": { + "External id": 1428844,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675651.989, "dur": 28.882, + "args": { + "External id": 1428845,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850675685.758, "dur": 5.379, + "args": { + "External id": 1428846,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850675687.414, "dur": 3.040, + "args": { + "External id": 1428847,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675689.429, "dur": 0.834, + "args": { + "External id": 1428848,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850675696.357, "dur": 47.281, + "args": { + "External id": 1428849,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850675697.623, "dur": 45.490, + "args": { + "External id": 1428850,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850675779.263, "dur": 19.407, + "args": { + "External id": 1428851,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850675806.171, "dur": 5.118, + "args": { + "External id": 1428852,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675809.304, "dur": 0.940, + "args": { + "External id": 1428853,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850675815.889, "dur": 56.730, + "args": { + "External id": 1428854,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850675816.902, "dur": 8.860, + "args": { + "External id": 1428855,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850675820.498, "dur": 4.574, + "args": { + "External id": 1428856,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675821.730, "dur": 3.200, + "args": { + "External id": 1428857,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850675826.374, "dur": 45.837, + "args": { + "External id": 1428858,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850675827.224, "dur": 44.276, + "args": { + "External id": 1428859,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850675877.232, "dur": 4.117, + "args": { + "External id": 1428860,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850675879.332, "dur": 0.665, + "args": { + "External id": 1428861,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850675887.675, "dur": 1.631, + "args": { + "External id": 1428862,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850675899.667, "dur": 8.372, + "args": { + "External id": 1428863,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850675901.949, "dur": 5.755, + "args": { + "External id": 1428864,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850676028.954, "dur": 249.685, + "args": { + "External id": 1428865,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850676031.762, "dur": 3.685, + "args": { + "External id": 1428866,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850676037.385, "dur": 240.692, + "args": { + "External id": 1428867,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850676038.974, "dur": 0.608, + "args": { + "External id": 1428868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850676043.556, "dur": 66.080, + "args": { + "External id": 1428869,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850676113.107, "dur": 3.888, + "args": { + "External id": 1428870,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676115.563, "dur": 1.083, + "args": { + "External id": 1428871,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850676118.051, "dur": 27.175, + "args": { + "External id": 1428872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850676119.361, "dur": 2.672, + "args": { + "External id": 1428873,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850676123.504, "dur": 21.299, + "args": { + "External id": 1428874,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676128.958, "dur": 3.209, + "args": { + "External id": 1428875,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850676146.722, "dur": 24.936, + "args": { + "External id": 1428876,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676173.736, "dur": 14.924, + "args": { + "External id": 1428877,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850676192.214, "dur": 15.898, + "args": { + "External id": 1428878,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676209.834, "dur": 13.932, + "args": { + "External id": 1428879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850676228.375, "dur": 21.203, + "args": { + "External id": 1428880,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676230.649, "dur": 1.604, + "args": { + "External id": 1428881,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676234.276, "dur": 0.643, + "args": { + "External id": 1428882,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676250.802, "dur": 12.718, + "args": { + "External id": 1428883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676264.624, "dur": 11.688, + "args": { + "External id": 1428884,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850676289.139, "dur": 2.942, + "args": { + "External id": 1428885,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850676303.279, "dur": 3.942, + "args": { + "External id": 1428886,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676305.861, "dur": 0.447, + "args": { + "External id": 1428887,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850676390.989, "dur": 76.000, + "args": { + "External id": 1428888,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850676473.223, "dur": 6.126, + "args": { + "External id": 1428889,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676476.653, "dur": 1.467, + "args": { + "External id": 1428890,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676481.037, "dur": 29.506, + "args": { + "External id": 1428891,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850676515.570, "dur": 8.307, + "args": { + "External id": 1428892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850676517.593, "dur": 5.435, + "args": { + "External id": 1428893,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676521.990, "dur": 0.832, + "args": { + "External id": 1428894,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850676527.170, "dur": 48.047, + "args": { + "External id": 1428895,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850676528.483, "dur": 45.935, + "args": { + "External id": 1428896,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676580.028, "dur": 15.936, + "args": { + "External id": 1428897,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850676602.631, "dur": 4.093, + "args": { + "External id": 1428898,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676605.209, "dur": 0.505, + "args": { + "External id": 1428899,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850676611.501, "dur": 56.298, + "args": { + "External id": 1428900,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850676614.815, "dur": 5.630, + "args": { + "External id": 1428901,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850676615.917, "dur": 3.777, + "args": { + "External id": 1428902,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676617.208, "dur": 2.250, + "args": { + "External id": 1428903,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850676621.381, "dur": 45.911, + "args": { + "External id": 1428904,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850676622.033, "dur": 44.418, + "args": { + "External id": 1428905,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850676672.700, "dur": 5.110, + "args": { + "External id": 1428906,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676675.030, "dur": 1.195, + "args": { + "External id": 1428907,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850676686.985, "dur": 1.667, + "args": { + "External id": 1428908,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850676698.151, "dur": 12.589, + "args": { + "External id": 1428909,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850676705.901, "dur": 4.504, + "args": { + "External id": 1428910,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850676806.692, "dur": 236.487, + "args": { + "External id": 1428911,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850676810.605, "dur": 2.444, + "args": { + "External id": 1428912,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850676814.557, "dur": 228.079, + "args": { + "External id": 1428913,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850676818.272, "dur": 0.733, + "args": { + "External id": 1428914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850676820.112, "dur": 22.617, + "args": { + "External id": 1428915,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850676844.386, "dur": 5.096, + "args": { + "External id": 1428916,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676848.168, "dur": 1.127, + "args": { + "External id": 1428917,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850676850.434, "dur": 23.694, + "args": { + "External id": 1428918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850676851.599, "dur": 1.379, + "args": { + "External id": 1428919,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850676854.221, "dur": 19.589, + "args": { + "External id": 1428920,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676856.605, "dur": 2.803, + "args": { + "External id": 1428921,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850676875.712, "dur": 23.423, + "args": { + "External id": 1428922,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676900.771, "dur": 18.359, + "args": { + "External id": 1428923,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850676924.318, "dur": 15.254, + "args": { + "External id": 1428924,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676941.032, "dur": 15.111, + "args": { + "External id": 1428925,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850676957.947, "dur": 45.870, + "args": { + "External id": 1428926,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850676959.858, "dur": 1.543, + "args": { + "External id": 1428927,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850676963.219, "dur": 0.915, + "args": { + "External id": 1428928,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677006.786, "dur": 17.915, + "args": { + "External id": 1428929,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677028.126, "dur": 13.086, + "args": { + "External id": 1428930,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850677052.249, "dur": 3.065, + "args": { + "External id": 1428931,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850677106.085, "dur": 6.670, + "args": { + "External id": 1428932,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677110.481, "dur": 0.938, + "args": { + "External id": 1428933,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850677200.582, "dur": 72.881, + "args": { + "External id": 1428934,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850677279.138, "dur": 5.596, + "args": { + "External id": 1428935,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677282.296, "dur": 0.994, + "args": { + "External id": 1428936,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677286.338, "dur": 30.552, + "args": { + "External id": 1428937,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850677324.896, "dur": 6.384, + "args": { + "External id": 1428938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850677326.944, "dur": 3.643, + "args": { + "External id": 1428939,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677328.899, "dur": 1.474, + "args": { + "External id": 1428940,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850677334.452, "dur": 49.710, + "args": { + "External id": 1428941,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850677335.817, "dur": 47.738, + "args": { + "External id": 1428942,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677388.775, "dur": 19.363, + "args": { + "External id": 1428943,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850677414.811, "dur": 6.725, + "args": { + "External id": 1428944,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677419.745, "dur": 0.761, + "args": { + "External id": 1428945,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850677426.069, "dur": 60.686, + "args": { + "External id": 1428946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850677432.241, "dur": 3.569, + "args": { + "External id": 1428947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850677433.129, "dur": 2.087, + "args": { + "External id": 1428948,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677434.450, "dur": 0.620, + "args": { + "External id": 1428949,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850677436.622, "dur": 49.650, + "args": { + "External id": 1428950,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850677439.990, "dur": 45.584, + "args": { + "External id": 1428951,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850677491.766, "dur": 4.578, + "args": { + "External id": 1428952,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677494.055, "dur": 0.905, + "args": { + "External id": 1428953,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850677502.809, "dur": 1.920, + "args": { + "External id": 1428954,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850677513.900, "dur": 9.228, + "args": { + "External id": 1428955,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850677516.196, "dur": 6.597, + "args": { + "External id": 1428956,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850677617.311, "dur": 193.778, + "args": { + "External id": 1428957,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850677619.406, "dur": 2.427, + "args": { + "External id": 1428958,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850677623.460, "dur": 187.108, + "args": { + "External id": 1428959,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850677624.880, "dur": 0.666, + "args": { + "External id": 1428960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850677626.799, "dur": 25.456, + "args": { + "External id": 1428961,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850677654.194, "dur": 3.126, + "args": { + "External id": 1428962,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677656.336, "dur": 0.678, + "args": { + "External id": 1428963,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850677658.297, "dur": 26.375, + "args": { + "External id": 1428964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850677659.589, "dur": 1.893, + "args": { + "External id": 1428965,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850677665.373, "dur": 18.867, + "args": { + "External id": 1428966,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677669.429, "dur": 2.594, + "args": { + "External id": 1428967,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850677686.119, "dur": 24.895, + "args": { + "External id": 1428968,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677712.739, "dur": 14.162, + "args": { + "External id": 1428969,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850677729.714, "dur": 14.707, + "args": { + "External id": 1428970,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677745.782, "dur": 13.152, + "args": { + "External id": 1428971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850677760.874, "dur": 19.680, + "args": { + "External id": 1428972,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677762.952, "dur": 1.602, + "args": { + "External id": 1428973,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677766.199, "dur": 0.464, + "args": { + "External id": 1428974,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677784.288, "dur": 12.182, + "args": { + "External id": 1428975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677797.689, "dur": 11.781, + "args": { + "External id": 1428976,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850677817.825, "dur": 1.961, + "args": { + "External id": 1428977,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850677828.620, "dur": 3.339, + "args": { + "External id": 1428978,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677830.585, "dur": 0.441, + "args": { + "External id": 1428979,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850677902.786, "dur": 53.221, + "args": { + "External id": 1428980,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850677961.500, "dur": 5.661, + "args": { + "External id": 1428981,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850677964.527, "dur": 1.393, + "args": { + "External id": 1428982,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850677970.852, "dur": 48.097, + "args": { + "External id": 1428983,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850678026.140, "dur": 5.892, + "args": { + "External id": 1428984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850678027.803, "dur": 3.380, + "args": { + "External id": 1428985,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678029.883, "dur": 1.114, + "args": { + "External id": 1428986,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850678035.233, "dur": 89.048, + "args": { + "External id": 1428987,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850678036.442, "dur": 86.310, + "args": { + "External id": 1428988,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678131.208, "dur": 18.130, + "args": { + "External id": 1428989,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850678157.340, "dur": 28.765, + "args": { + "External id": 1428990,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850678160.620, "dur": 24.949, + "args": { + "External id": 1428991,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678167.786, "dur": 0.968, + "args": { + "External id": 1428992,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850678287.241, "dur": 32.241, + "args": { + "External id": 1428993,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850678289.811, "dur": 29.385, + "args": { + "External id": 1428994,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 15430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678295.411, "dur": 5.151, + "args": { + "External id": 1428995,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678301.886, "dur": 16.701, + "args": { + "External id": 1428996,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850678335.407, "dur": 8.142, + "args": { + "External id": 1428997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850678339.978, "dur": 3.189, + "args": { + "External id": 1428998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850678344.793, "dur": 1.053, + "args": { + "External id": 1428999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850678345.129, "dur": 0.620, + "args": { + "External id": 1429000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678393.751, "dur": 25.887, + "args": { + "External id": 1429001,"Sequence number": 15348866, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678422.141, "dur": 13.517, + "args": { + "External id": 1429002,"Sequence number": 15348867, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15438 + } + }, + { + "ph": "s", "id": 16, "pid": 2338706, "tid": 2338706, "ts": 6413850678422.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850678443.575, "dur": 7.742, + "args": { + "External id": 1429003,"Sequence number": 15348868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 15439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678447.760, "dur": 1.516, + "args": { + "External id": 1429004,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850678454.498, "dur": 11.907, + "args": { + "External id": 1429005,"Sequence number": 15348868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 15441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678461.822, "dur": 3.010, + "args": { + "External id": 1429006,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850678467.813, "dur": 2.752, + "args": { + "External id": 1429007,"Sequence number": 15348868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 15443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678469.401, "dur": 0.493, + "args": { + "External id": 1429008,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 15444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850678475.941, "dur": 6.440, + "args": { + "External id": 1429009,"Sequence number": 15348868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15445 + } + }, + { + "ph": "s", "id": 15, "pid": 2338706, "tid": 2338706, "ts": 6413850678475.941, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678479.785, "dur": 0.956, + "args": { + "External id": 1429010,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850678485.822, "dur": 7.078, + "args": { + "External id": 1429011,"Sequence number": 15348869, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15447 + } + }, + { + "ph": "s", "id": 14, "pid": 2338706, "tid": 2338706, "ts": 6413850678485.822, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678491.368, "dur": 0.642, + "args": { + "External id": 1429012,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850678493.932, "dur": 5.058, + "args": { + "External id": 1429013,"Sequence number": 15348870, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 15449 + } + }, + { + "ph": "s", "id": 13, "pid": 2338706, "tid": 2338706, "ts": 6413850678493.932, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678497.365, "dur": 0.597, + "args": { + "External id": 1429014,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850678500.060, "dur": 4.367, + "args": { + "External id": 1429015,"Sequence number": 15348871, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 15451 + } + }, + { + "ph": "s", "id": 12, "pid": 2338706, "tid": 2338706, "ts": 6413850678500.060, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678502.460, "dur": 1.081, + "args": { + "External id": 1429016,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 15452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850678508.997, "dur": 34.920, + "args": { + "External id": 1429017,"Sequence number": 15348872, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850678512.943, "dur": 30.742, + "args": { + "External id": 1429018,"Sequence number": 15348872, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850678515.632, "dur": 7.543, + "args": { + "External id": 1429019,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 15455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850678518.381, "dur": 4.171, + "args": { + "External id": 1429020,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678524.110, "dur": 19.055, + "args": { + "External id": 1429021,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 15457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850678574.004, "dur": 4.534, + "args": { + "External id": 1429022,"Sequence number": 15348872, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 15458 + } + }, + { + "ph": "s", "id": 11, "pid": 2338706, "tid": 2338706, "ts": 6413850678574.004, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850678581.330, "dur": 3.952, + "args": { + "External id": 1429023,"Sequence number": 15348873, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850678626.318, "dur": 43989.867, + "args": { + "External id": 1429024,"Sequence number": 15348873, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 15460 + } + }, + { + "ph": "s", "id": 10, "pid": 2338706, "tid": 2338706, "ts": 6413850678626.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850678645.580, "dur": 29.462, + "args": { + "External id": 1429025,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850678646.260, "dur": 28.567, + "args": { + "External id": 1429026,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850678647.912, "dur": 5.810, + "args": { + "External id": 1429027,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850678649.256, "dur": 3.819, + "args": { + "External id": 1429028,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678654.405, "dur": 19.922, + "args": { + "External id": 1429029,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 15465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850678693.989, "dur": 28.940, + "args": { + "External id": 1429030,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850678695.003, "dur": 6.458, + "args": { + "External id": 1429031,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678697.114, "dur": 3.962, + "args": { + "External id": 1429032,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678703.083, "dur": 19.588, + "args": { + "External id": 1429033,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678707.376, "dur": 14.753, + "args": { + "External id": 1429034,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850678726.669, "dur": 18.917, + "args": { + "External id": 1429035,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850678727.396, "dur": 3.868, + "args": { + "External id": 1429036,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678728.343, "dur": 2.663, + "args": { + "External id": 1429037,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678731.800, "dur": 13.556, + "args": { + "External id": 1429038,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678732.330, "dur": 12.626, + "args": { + "External id": 1429039,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 15475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850678752.737, "dur": 21.425, + "args": { + "External id": 1429040,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 15476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850678754.549, "dur": 2.904, + "args": { + "External id": 1429041,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678758.214, "dur": 15.612, + "args": { + "External id": 1429042,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 15478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678763.057, "dur": 10.312, + "args": { + "External id": 1429043,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413850678779.562, "dur": 27.344, + "args": { + "External id": 1429044,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850678810.276, "dur": 84.871, + "args": { + "External id": 1429045,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850678812.461, "dur": 82.074, + "args": { + "External id": 1429046,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678818.670, "dur": 0.851, + "args": { + "External id": 1429047,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850678820.955, "dur": 35.029, + "args": { + "External id": 1429048,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850678822.417, "dur": 33.316, + "args": { + "External id": 1429049,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 15485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850678824.839, "dur": 6.871, + "args": { + "External id": 1429050,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850678832.618, "dur": 22.687, + "args": { + "External id": 1429051,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 15487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413850678903.004, "dur": 36925.866, + "args": { + "External id": 1429052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413850678904.519, "dur": 36921.768, + "args": { + "External id": 1429053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850715850.878, "dur": 13.047, + "args": { + "External id": 1429054,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850715858.606, "dur": 1.879, + "args": { + "External id": 1429055,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850715871.883, "dur": 162.972, + "args": { + "External id": 1429056,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850715873.652, "dur": 10.068, + "args": { + "External id": 1429057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850715877.547, "dur": 5.063, + "args": { + "External id": 1429058,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850715880.243, "dur": 2.009, + "args": { + "External id": 1429059,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850715888.000, "dur": 144.755, + "args": { + "External id": 1429060,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850715890.156, "dur": 140.873, + "args": { + "External id": 1429061,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850716042.248, "dur": 7.559, + "args": { + "External id": 1429062,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716045.770, "dur": 1.809, + "args": { + "External id": 1429063,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850716090.769, "dur": 5.089, + "args": { + "External id": 1429064,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850716110.630, "dur": 14.319, + "args": { + "External id": 1429065,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850716117.176, "dur": 7.419, + "args": { + "External id": 1429066,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850716313.544, "dur": 240.984, + "args": { + "External id": 1429067,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850716319.324, "dur": 3.846, + "args": { + "External id": 1429068,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850716324.999, "dur": 228.867, + "args": { + "External id": 1429069,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850716327.174, "dur": 0.551, + "args": { + "External id": 1429070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850716329.473, "dur": 37.137, + "args": { + "External id": 1429071,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850716368.954, "dur": 4.040, + "args": { + "External id": 1429072,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716371.698, "dur": 0.907, + "args": { + "External id": 1429073,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850716374.289, "dur": 34.183, + "args": { + "External id": 1429074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850716378.248, "dur": 1.616, + "args": { + "External id": 1429075,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850716381.454, "dur": 26.625, + "args": { + "External id": 1429076,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716387.725, "dur": 3.417, + "args": { + "External id": 1429077,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850716410.519, "dur": 26.328, + "args": { + "External id": 1429078,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716439.110, "dur": 16.969, + "args": { + "External id": 1429079,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850716459.670, "dur": 18.074, + "args": { + "External id": 1429080,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716479.650, "dur": 15.682, + "args": { + "External id": 1429081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850716497.727, "dur": 23.806, + "args": { + "External id": 1429082,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716500.208, "dur": 1.513, + "args": { + "External id": 1429083,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716506.393, "dur": 0.762, + "args": { + "External id": 1429084,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716523.244, "dur": 14.403, + "args": { + "External id": 1429085,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716539.140, "dur": 13.500, + "args": { + "External id": 1429086,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850716562.839, "dur": 2.312, + "args": { + "External id": 1429087,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850716573.926, "dur": 5.702, + "args": { + "External id": 1429088,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716577.756, "dur": 0.675, + "args": { + "External id": 1429089,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850716668.863, "dur": 90.591, + "args": { + "External id": 1429090,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850716768.810, "dur": 10.888, + "args": { + "External id": 1429091,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716773.334, "dur": 3.521, + "args": { + "External id": 1429092,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716781.665, "dur": 36.812, + "args": { + "External id": 1429093,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850716825.114, "dur": 6.406, + "args": { + "External id": 1429094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850716827.200, "dur": 3.574, + "args": { + "External id": 1429095,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716829.360, "dur": 1.103, + "args": { + "External id": 1429096,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850716837.322, "dur": 54.174, + "args": { + "External id": 1429097,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850716838.660, "dur": 51.862, + "args": { + "External id": 1429098,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850716896.792, "dur": 18.958, + "args": { + "External id": 1429099,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850716923.096, "dur": 4.351, + "args": { + "External id": 1429100,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716925.460, "dur": 0.810, + "args": { + "External id": 1429101,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850716932.684, "dur": 76.798, + "args": { + "External id": 1429102,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850716934.028, "dur": 8.036, + "args": { + "External id": 1429103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850716937.790, "dur": 3.580, + "args": { + "External id": 1429104,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850716940.556, "dur": 0.602, + "args": { + "External id": 1429105,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850716942.843, "dur": 65.942, + "args": { + "External id": 1429106,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850716943.507, "dur": 64.160, + "args": { + "External id": 1429107,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850717016.802, "dur": 6.389, + "args": { + "External id": 1429108,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717019.652, "dur": 1.763, + "args": { + "External id": 1429109,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850717033.474, "dur": 2.363, + "args": { + "External id": 1429110,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850717048.982, "dur": 62.506, + "args": { + "External id": 1429111,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850717103.056, "dur": 7.742, + "args": { + "External id": 1429112,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850717240.445, "dur": 211.794, + "args": { + "External id": 1429113,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850717244.695, "dur": 4.721, + "args": { + "External id": 1429114,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850717251.105, "dur": 200.648, + "args": { + "External id": 1429115,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850717257.368, "dur": 0.492, + "args": { + "External id": 1429116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850717259.097, "dur": 26.365, + "args": { + "External id": 1429117,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850717287.452, "dur": 3.468, + "args": { + "External id": 1429118,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717289.677, "dur": 0.948, + "args": { + "External id": 1429119,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850717291.784, "dur": 26.493, + "args": { + "External id": 1429120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850717295.044, "dur": 1.359, + "args": { + "External id": 1429121,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850717297.734, "dur": 20.221, + "args": { + "External id": 1429122,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717301.221, "dur": 2.782, + "args": { + "External id": 1429123,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850717319.925, "dur": 23.484, + "args": { + "External id": 1429124,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717345.480, "dur": 17.130, + "args": { + "External id": 1429125,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850717368.180, "dur": 14.979, + "args": { + "External id": 1429126,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717385.000, "dur": 14.183, + "args": { + "External id": 1429127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850717401.322, "dur": 21.639, + "args": { + "External id": 1429128,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717403.671, "dur": 1.675, + "args": { + "External id": 1429129,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717407.447, "dur": 0.854, + "args": { + "External id": 1429130,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717424.619, "dur": 13.009, + "args": { + "External id": 1429131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717438.993, "dur": 11.550, + "args": { + "External id": 1429132,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850717462.477, "dur": 2.820, + "args": { + "External id": 1429133,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850717477.052, "dur": 5.531, + "args": { + "External id": 1429134,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717479.818, "dur": 0.647, + "args": { + "External id": 1429135,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850717563.685, "dur": 73.913, + "args": { + "External id": 1429136,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850717643.689, "dur": 6.385, + "args": { + "External id": 1429137,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717646.409, "dur": 2.360, + "args": { + "External id": 1429138,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717652.080, "dur": 32.063, + "args": { + "External id": 1429139,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850717689.700, "dur": 10.487, + "args": { + "External id": 1429140,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850717691.433, "dur": 8.017, + "args": { + "External id": 1429141,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717695.805, "dur": 3.278, + "args": { + "External id": 1429142,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850717703.454, "dur": 53.792, + "args": { + "External id": 1429143,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850717704.743, "dur": 51.751, + "args": { + "External id": 1429144,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850717762.509, "dur": 21.620, + "args": { + "External id": 1429145,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850717803.271, "dur": 5.513, + "args": { + "External id": 1429146,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717807.011, "dur": 0.742, + "args": { + "External id": 1429147,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850717816.466, "dur": 51.719, + "args": { + "External id": 1429148,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850717817.433, "dur": 3.969, + "args": { + "External id": 1429149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850717818.418, "dur": 2.258, + "args": { + "External id": 1429150,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717819.904, "dur": 0.597, + "args": { + "External id": 1429151,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850717822.070, "dur": 45.618, + "args": { + "External id": 1429152,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850717822.831, "dur": 44.377, + "args": { + "External id": 1429153,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850717873.218, "dur": 4.087, + "args": { + "External id": 1429154,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850717875.481, "dur": 0.600, + "args": { + "External id": 1429155,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850717886.314, "dur": 1.941, + "args": { + "External id": 1429156,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850717896.938, "dur": 8.151, + "args": { + "External id": 1429157,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850717898.837, "dur": 5.901, + "args": { + "External id": 1429158,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850718038.876, "dur": 268.893, + "args": { + "External id": 1429159,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850718042.871, "dur": 3.376, + "args": { + "External id": 1429160,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850718048.132, "dur": 259.088, + "args": { + "External id": 1429161,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850718086.637, "dur": 0.876, + "args": { + "External id": 1429162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850718090.814, "dur": 36.748, + "args": { + "External id": 1429163,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850718129.463, "dur": 3.573, + "args": { + "External id": 1429164,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718131.714, "dur": 1.020, + "args": { + "External id": 1429165,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850718133.867, "dur": 27.057, + "args": { + "External id": 1429166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850718135.246, "dur": 1.709, + "args": { + "External id": 1429167,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850718138.354, "dur": 22.227, + "args": { + "External id": 1429168,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718143.277, "dur": 3.048, + "args": { + "External id": 1429169,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850718162.457, "dur": 25.943, + "args": { + "External id": 1429170,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718190.254, "dur": 14.963, + "args": { + "External id": 1429171,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850718210.652, "dur": 17.891, + "args": { + "External id": 1429172,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718230.249, "dur": 14.754, + "args": { + "External id": 1429173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850718246.939, "dur": 25.073, + "args": { + "External id": 1429174,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718249.183, "dur": 1.587, + "args": { + "External id": 1429175,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718252.555, "dur": 0.945, + "args": { + "External id": 1429176,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718273.442, "dur": 14.908, + "args": { + "External id": 1429177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718292.712, "dur": 13.411, + "args": { + "External id": 1429178,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850718317.275, "dur": 2.741, + "args": { + "External id": 1429179,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850718331.410, "dur": 5.723, + "args": { + "External id": 1429180,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718334.106, "dur": 0.834, + "args": { + "External id": 1429181,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850718422.012, "dur": 69.646, + "args": { + "External id": 1429182,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850718498.113, "dur": 5.764, + "args": { + "External id": 1429183,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718501.323, "dur": 1.091, + "args": { + "External id": 1429184,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718505.769, "dur": 30.688, + "args": { + "External id": 1429185,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850718544.054, "dur": 6.037, + "args": { + "External id": 1429186,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850718545.937, "dur": 3.420, + "args": { + "External id": 1429187,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718548.148, "dur": 1.010, + "args": { + "External id": 1429188,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850718553.147, "dur": 50.672, + "args": { + "External id": 1429189,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850718554.205, "dur": 48.952, + "args": { + "External id": 1429190,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718608.615, "dur": 19.083, + "args": { + "External id": 1429191,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850718634.669, "dur": 6.983, + "args": { + "External id": 1429192,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718639.953, "dur": 0.637, + "args": { + "External id": 1429193,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850718646.666, "dur": 62.029, + "args": { + "External id": 1429194,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850718647.782, "dur": 5.320, + "args": { + "External id": 1429195,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850718648.888, "dur": 3.537, + "args": { + "External id": 1429196,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718650.288, "dur": 1.897, + "args": { + "External id": 1429197,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850718653.992, "dur": 54.155, + "args": { + "External id": 1429198,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850718662.427, "dur": 44.811, + "args": { + "External id": 1429199,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850718713.294, "dur": 4.352, + "args": { + "External id": 1429200,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718715.590, "dur": 0.705, + "args": { + "External id": 1429201,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850718724.459, "dur": 1.778, + "args": { + "External id": 1429202,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850718735.435, "dur": 9.334, + "args": { + "External id": 1429203,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850718740.332, "dur": 4.096, + "args": { + "External id": 1429204,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850718849.673, "dur": 270.909, + "args": { + "External id": 1429205,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850718853.537, "dur": 2.233, + "args": { + "External id": 1429206,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850718857.769, "dur": 261.971, + "args": { + "External id": 1429207,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850718859.280, "dur": 0.488, + "args": { + "External id": 1429208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850718860.865, "dur": 23.251, + "args": { + "External id": 1429209,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850718885.733, "dur": 6.224, + "args": { + "External id": 1429210,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850718889.280, "dur": 2.447, + "args": { + "External id": 1429211,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850718892.862, "dur": 25.750, + "args": { + "External id": 1429212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850718896.342, "dur": 1.427, + "args": { + "External id": 1429213,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850718899.144, "dur": 19.092, + "args": { + "External id": 1429214,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718901.877, "dur": 2.200, + "args": { + "External id": 1429215,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850718920.045, "dur": 22.668, + "args": { + "External id": 1429216,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850718944.428, "dur": 16.702, + "args": { + "External id": 1429217,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850718963.823, "dur": 35.125, + "args": { + "External id": 1429218,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719001.665, "dur": 16.082, + "args": { + "External id": 1429219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850719019.954, "dur": 27.888, + "args": { + "External id": 1429220,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719024.510, "dur": 2.452, + "args": { + "External id": 1429221,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719031.583, "dur": 0.824, + "args": { + "External id": 1429222,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719049.664, "dur": 53.204, + "args": { + "External id": 1429223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719105.629, "dur": 12.063, + "args": { + "External id": 1429224,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850719130.788, "dur": 3.128, + "args": { + "External id": 1429225,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850719144.882, "dur": 4.759, + "args": { + "External id": 1429226,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719147.716, "dur": 0.775, + "args": { + "External id": 1429227,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850719235.013, "dur": 67.739, + "args": { + "External id": 1429228,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850719308.759, "dur": 7.754, + "args": { + "External id": 1429229,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719314.393, "dur": 0.773, + "args": { + "External id": 1429230,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719318.163, "dur": 29.298, + "args": { + "External id": 1429231,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850719352.841, "dur": 6.580, + "args": { + "External id": 1429232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850719354.661, "dur": 4.005, + "args": { + "External id": 1429233,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719356.758, "dur": 1.680, + "args": { + "External id": 1429234,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850719362.625, "dur": 45.625, + "args": { + "External id": 1429235,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850719363.865, "dur": 43.421, + "args": { + "External id": 1429236,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719412.813, "dur": 16.129, + "args": { + "External id": 1429237,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850719437.902, "dur": 6.456, + "args": { + "External id": 1429238,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719440.170, "dur": 3.292, + "args": { + "External id": 1429239,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850719449.143, "dur": 56.226, + "args": { + "External id": 1429240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850719450.522, "dur": 6.221, + "args": { + "External id": 1429241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850719451.198, "dur": 4.904, + "args": { + "External id": 1429242,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719455.300, "dur": 0.620, + "args": { + "External id": 1429243,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850719457.495, "dur": 47.338, + "args": { + "External id": 1429244,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850719458.264, "dur": 45.839, + "args": { + "External id": 1429245,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850719509.928, "dur": 4.277, + "args": { + "External id": 1429246,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719512.188, "dur": 0.661, + "args": { + "External id": 1429247,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850719520.213, "dur": 1.603, + "args": { + "External id": 1429248,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850719530.480, "dur": 9.747, + "args": { + "External id": 1429249,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850719535.044, "dur": 4.808, + "args": { + "External id": 1429250,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850719639.114, "dur": 204.974, + "args": { + "External id": 1429251,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850719643.241, "dur": 2.272, + "args": { + "External id": 1429252,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850719646.918, "dur": 196.471, + "args": { + "External id": 1429253,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850719648.317, "dur": 0.604, + "args": { + "External id": 1429254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850719650.438, "dur": 21.600, + "args": { + "External id": 1429255,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850719673.613, "dur": 4.855, + "args": { + "External id": 1429256,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719677.569, "dur": 0.592, + "args": { + "External id": 1429257,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850719679.495, "dur": 27.886, + "args": { + "External id": 1429258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850719683.099, "dur": 3.717, + "args": { + "External id": 1429259,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850719688.205, "dur": 18.863, + "args": { + "External id": 1429260,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719691.497, "dur": 2.771, + "args": { + "External id": 1429261,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850719708.956, "dur": 22.616, + "args": { + "External id": 1429262,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719733.188, "dur": 14.521, + "args": { + "External id": 1429263,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850719750.319, "dur": 17.169, + "args": { + "External id": 1429264,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719769.095, "dur": 15.767, + "args": { + "External id": 1429265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850719786.668, "dur": 24.597, + "args": { + "External id": 1429266,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719788.718, "dur": 1.310, + "args": { + "External id": 1429267,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719794.774, "dur": 0.410, + "args": { + "External id": 1429268,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719812.656, "dur": 14.639, + "args": { + "External id": 1429269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850719828.478, "dur": 13.972, + "args": { + "External id": 1429270,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850719851.267, "dur": 1.754, + "args": { + "External id": 1429271,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850719862.844, "dur": 3.657, + "args": { + "External id": 1429272,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850719865.182, "dur": 0.367, + "args": { + "External id": 1429273,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850719938.220, "dur": 77.562, + "args": { + "External id": 1429274,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850720026.042, "dur": 6.696, + "args": { + "External id": 1429275,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720029.671, "dur": 1.123, + "args": { + "External id": 1429276,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720034.520, "dur": 71.025, + "args": { + "External id": 1429277,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850720113.074, "dur": 6.974, + "args": { + "External id": 1429278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850720114.826, "dur": 4.291, + "args": { + "External id": 1429279,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720117.288, "dur": 1.602, + "args": { + "External id": 1429280,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850720125.960, "dur": 53.204, + "args": { + "External id": 1429281,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850720127.062, "dur": 51.382, + "args": { + "External id": 1429282,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720183.779, "dur": 19.643, + "args": { + "External id": 1429283,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850720210.646, "dur": 4.647, + "args": { + "External id": 1429284,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720213.296, "dur": 0.788, + "args": { + "External id": 1429285,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850720219.715, "dur": 55.620, + "args": { + "External id": 1429286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850720220.683, "dur": 8.877, + "args": { + "External id": 1429287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850720224.066, "dur": 4.755, + "args": { + "External id": 1429288,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720225.295, "dur": 3.326, + "args": { + "External id": 1429289,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850720230.281, "dur": 44.627, + "args": { + "External id": 1429290,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850720231.242, "dur": 42.957, + "args": { + "External id": 1429291,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850720279.574, "dur": 5.629, + "args": { + "External id": 1429292,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720281.691, "dur": 2.107, + "args": { + "External id": 1429293,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850720295.246, "dur": 1.861, + "args": { + "External id": 1429294,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850720306.090, "dur": 7.160, + "args": { + "External id": 1429295,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850720308.345, "dur": 4.608, + "args": { + "External id": 1429296,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850720414.869, "dur": 207.115, + "args": { + "External id": 1429297,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850720416.984, "dur": 2.135, + "args": { + "External id": 1429298,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850720420.756, "dur": 200.667, + "args": { + "External id": 1429299,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850720424.602, "dur": 0.467, + "args": { + "External id": 1429300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850720426.304, "dur": 25.258, + "args": { + "External id": 1429301,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850720453.342, "dur": 3.315, + "args": { + "External id": 1429302,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720455.502, "dur": 0.802, + "args": { + "External id": 1429303,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850720457.708, "dur": 25.096, + "args": { + "External id": 1429304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850720458.683, "dur": 1.345, + "args": { + "External id": 1429305,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850720461.160, "dur": 21.199, + "args": { + "External id": 1429306,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720465.660, "dur": 2.535, + "args": { + "External id": 1429307,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850720484.410, "dur": 24.770, + "args": { + "External id": 1429308,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720510.855, "dur": 16.718, + "args": { + "External id": 1429309,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850720532.393, "dur": 16.086, + "args": { + "External id": 1429310,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720549.789, "dur": 15.484, + "args": { + "External id": 1429311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850720567.101, "dur": 22.136, + "args": { + "External id": 1429312,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720569.215, "dur": 1.542, + "args": { + "External id": 1429313,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720572.810, "dur": 0.797, + "args": { + "External id": 1429314,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720591.010, "dur": 15.217, + "args": { + "External id": 1429315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720607.321, "dur": 12.708, + "args": { + "External id": 1429316,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850720631.595, "dur": 1.672, + "args": { + "External id": 1429317,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850720643.485, "dur": 3.672, + "args": { + "External id": 1429318,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720645.755, "dur": 0.360, + "args": { + "External id": 1429319,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850720723.877, "dur": 58.159, + "args": { + "External id": 1429320,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850720787.450, "dur": 5.001, + "args": { + "External id": 1429321,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720790.327, "dur": 1.057, + "args": { + "External id": 1429322,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720794.066, "dur": 28.219, + "args": { + "External id": 1429323,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850720827.318, "dur": 7.706, + "args": { + "External id": 1429324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850720828.917, "dur": 5.418, + "args": { + "External id": 1429325,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720833.058, "dur": 1.063, + "args": { + "External id": 1429326,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850720837.690, "dur": 45.995, + "args": { + "External id": 1429327,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850720838.839, "dur": 44.118, + "args": { + "External id": 1429328,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850720887.725, "dur": 18.337, + "args": { + "External id": 1429329,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850720912.282, "dur": 3.670, + "args": { + "External id": 1429330,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720914.416, "dur": 0.636, + "args": { + "External id": 1429331,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850720922.503, "dur": 71.464, + "args": { + "External id": 1429332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850720923.485, "dur": 5.820, + "args": { + "External id": 1429333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850720924.232, "dur": 4.307, + "args": { + "External id": 1429334,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850720927.865, "dur": 0.534, + "args": { + "External id": 1429335,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850720929.932, "dur": 63.487, + "args": { + "External id": 1429336,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850720930.775, "dur": 61.565, + "args": { + "External id": 1429337,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850721001.268, "dur": 4.975, + "args": { + "External id": 1429338,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721004.106, "dur": 0.760, + "args": { + "External id": 1429339,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850721016.344, "dur": 2.063, + "args": { + "External id": 1429340,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721027.671, "dur": 7.237, + "args": { + "External id": 1429341,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721029.701, "dur": 4.919, + "args": { + "External id": 1429342,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850721185.523, "dur": 220.670, + "args": { + "External id": 1429343,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721188.575, "dur": 3.751, + "args": { + "External id": 1429344,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850721194.020, "dur": 211.725, + "args": { + "External id": 1429345,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850721198.890, "dur": 0.484, + "args": { + "External id": 1429346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850721200.732, "dur": 27.218, + "args": { + "External id": 1429347,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850721229.415, "dur": 3.596, + "args": { + "External id": 1429348,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721231.495, "dur": 1.117, + "args": { + "External id": 1429349,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850721234.131, "dur": 26.604, + "args": { + "External id": 1429350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721236.721, "dur": 1.634, + "args": { + "External id": 1429351,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850721239.695, "dur": 20.690, + "args": { + "External id": 1429352,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721243.274, "dur": 2.959, + "args": { + "External id": 1429353,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850721262.408, "dur": 26.323, + "args": { + "External id": 1429354,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721290.529, "dur": 15.852, + "args": { + "External id": 1429355,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850721311.871, "dur": 17.240, + "args": { + "External id": 1429356,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721330.619, "dur": 14.835, + "args": { + "External id": 1429357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850721347.404, "dur": 23.402, + "args": { + "External id": 1429358,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721349.765, "dur": 1.886, + "args": { + "External id": 1429359,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721353.539, "dur": 0.643, + "args": { + "External id": 1429360,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721372.396, "dur": 14.425, + "args": { + "External id": 1429361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721390.468, "dur": 14.139, + "args": { + "External id": 1429362,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850721414.064, "dur": 2.407, + "args": { + "External id": 1429363,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850721426.243, "dur": 4.490, + "args": { + "External id": 1429364,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721429.175, "dur": 0.566, + "args": { + "External id": 1429365,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850721504.840, "dur": 70.431, + "args": { + "External id": 1429366,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850721580.884, "dur": 6.907, + "args": { + "External id": 1429367,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721583.938, "dur": 2.575, + "args": { + "External id": 1429368,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721589.551, "dur": 30.114, + "args": { + "External id": 1429369,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850721627.045, "dur": 5.720, + "args": { + "External id": 1429370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850721628.853, "dur": 3.203, + "args": { + "External id": 1429371,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721630.664, "dur": 1.127, + "args": { + "External id": 1429372,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850721635.830, "dur": 46.998, + "args": { + "External id": 1429373,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850721637.123, "dur": 44.921, + "args": { + "External id": 1429374,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721687.518, "dur": 17.562, + "args": { + "External id": 1429375,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850721711.526, "dur": 6.207, + "args": { + "External id": 1429376,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721716.120, "dur": 0.584, + "args": { + "External id": 1429377,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850721722.113, "dur": 55.680, + "args": { + "External id": 1429378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850721723.038, "dur": 4.157, + "args": { + "External id": 1429379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850721723.862, "dur": 2.579, + "args": { + "External id": 1429380,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721725.685, "dur": 0.570, + "args": { + "External id": 1429381,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850721727.806, "dur": 49.637, + "args": { + "External id": 1429382,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850721730.896, "dur": 45.850, + "args": { + "External id": 1429383,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850721782.105, "dur": 3.895, + "args": { + "External id": 1429384,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721784.006, "dur": 0.620, + "args": { + "External id": 1429385,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850721791.980, "dur": 1.492, + "args": { + "External id": 1429386,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721801.471, "dur": 9.401, + "args": { + "External id": 1429387,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721806.153, "dur": 4.347, + "args": { + "External id": 1429388,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850721918.994, "dur": 274.551, + "args": { + "External id": 1429389,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721921.478, "dur": 4.311, + "args": { + "External id": 1429390,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850721927.075, "dur": 265.568, + "args": { + "External id": 1429391,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850721928.472, "dur": 0.332, + "args": { + "External id": 1429392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850721929.975, "dur": 23.676, + "args": { + "External id": 1429393,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850721955.080, "dur": 5.432, + "args": { + "External id": 1429394,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850721959.572, "dur": 0.730, + "args": { + "External id": 1429395,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850721964.180, "dur": 42.754, + "args": { + "External id": 1429396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850721965.310, "dur": 1.296, + "args": { + "External id": 1429397,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850721967.964, "dur": 38.325, + "args": { + "External id": 1429398,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850721970.441, "dur": 2.456, + "args": { + "External id": 1429399,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850722009.046, "dur": 26.926, + "args": { + "External id": 1429400,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722037.591, "dur": 16.575, + "args": { + "External id": 1429401,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850722093.516, "dur": 19.925, + "args": { + "External id": 1429402,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722115.272, "dur": 14.724, + "args": { + "External id": 1429403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850722132.156, "dur": 28.590, + "args": { + "External id": 1429404,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722136.112, "dur": 2.224, + "args": { + "External id": 1429405,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722142.887, "dur": 0.688, + "args": { + "External id": 1429406,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722162.548, "dur": 14.582, + "args": { + "External id": 1429407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722178.432, "dur": 12.783, + "args": { + "External id": 1429408,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850722203.497, "dur": 2.653, + "args": { + "External id": 1429409,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722216.595, "dur": 3.988, + "args": { + "External id": 1429410,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722218.999, "dur": 0.580, + "args": { + "External id": 1429411,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850722302.497, "dur": 65.129, + "args": { + "External id": 1429412,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722373.414, "dur": 7.477, + "args": { + "External id": 1429413,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722378.966, "dur": 0.693, + "args": { + "External id": 1429414,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722382.577, "dur": 29.474, + "args": { + "External id": 1429415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850722417.144, "dur": 5.975, + "args": { + "External id": 1429416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850722418.974, "dur": 3.386, + "args": { + "External id": 1429417,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722420.737, "dur": 1.369, + "args": { + "External id": 1429418,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850722426.192, "dur": 49.327, + "args": { + "External id": 1429419,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850722429.824, "dur": 44.965, + "args": { + "External id": 1429420,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722479.597, "dur": 17.773, + "args": { + "External id": 1429421,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850722502.373, "dur": 26.540, + "args": { + "External id": 1429422,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850722504.846, "dur": 23.579, + "args": { + "External id": 1429423,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722510.556, "dur": 0.885, + "args": { + "External id": 1429424,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850722534.620, "dur": 31.125, + "args": { + "External id": 1429425,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850722536.725, "dur": 28.748, + "args": { + "External id": 1429426,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 15862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722541.681, "dur": 3.819, + "args": { + "External id": 1429427,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722546.542, "dur": 18.237, + "args": { + "External id": 1429428,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850722581.345, "dur": 5.431, + "args": { + "External id": 1429429,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850722583.316, "dur": 3.077, + "args": { + "External id": 1429430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850722587.985, "dur": 1.221, + "args": { + "External id": 1429431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850722588.446, "dur": 0.673, + "args": { + "External id": 1429432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722635.321, "dur": 23.509, + "args": { + "External id": 1429433,"Sequence number": 15348874, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722663.366, "dur": 14.505, + "args": { + "External id": 1429434,"Sequence number": 15348875, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 15870 + } + }, + { + "ph": "s", "id": 9, "pid": 2338706, "tid": 2338706, "ts": 6413850722663.366, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722684.676, "dur": 6.551, + "args": { + "External id": 1429435,"Sequence number": 15348876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 15871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722688.367, "dur": 1.242, + "args": { + "External id": 1429436,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850722694.247, "dur": 9.372, + "args": { + "External id": 1429437,"Sequence number": 15348876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "3"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 15873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722699.028, "dur": 3.164, + "args": { + "External id": 1429438,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 15874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722705.077, "dur": 4.956, + "args": { + "External id": 1429439,"Sequence number": 15348876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 15875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722708.634, "dur": 0.734, + "args": { + "External id": 1429440,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 15876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722715.164, "dur": 6.508, + "args": { + "External id": 1429441,"Sequence number": 15348876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15877 + } + }, + { + "ph": "s", "id": 8, "pid": 2338706, "tid": 2338706, "ts": 6413850722715.164, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722719.042, "dur": 1.091, + "args": { + "External id": 1429442,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722722.825, "dur": 4.934, + "args": { + "External id": 1429443,"Sequence number": 15348877, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 15879 + } + }, + { + "ph": "s", "id": 7, "pid": 2338706, "tid": 2338706, "ts": 6413850722722.825, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722726.181, "dur": 0.634, + "args": { + "External id": 1429444,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413850722729.065, "dur": 13.120, + "args": { + "External id": 1429445,"Sequence number": 15348878, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 15881 + } + }, + { + "ph": "s", "id": 6, "pid": 2338706, "tid": 2338706, "ts": 6413850722729.065, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722740.263, "dur": 0.846, + "args": { + "External id": 1429446,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 15882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850722743.443, "dur": 5.717, + "args": { + "External id": 1429447,"Sequence number": 15348879, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 15883 + } + }, + { + "ph": "s", "id": 5, "pid": 2338706, "tid": 2338706, "ts": 6413850722743.443, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722745.804, "dur": 2.357, + "args": { + "External id": 1429448,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 15884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850722753.848, "dur": 31.669, + "args": { + "External id": 1429449,"Sequence number": 15348880, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850722755.498, "dur": 29.690, + "args": { + "External id": 1429450,"Sequence number": 15348880, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850722758.312, "dur": 7.379, + "args": { + "External id": 1429451,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 15887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850722761.175, "dur": 3.936, + "args": { + "External id": 1429452,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722766.635, "dur": 18.022, + "args": { + "External id": 1429453,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 15889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850722816.003, "dur": 4.544, + "args": { + "External id": 1429454,"Sequence number": 15348880, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 15890 + } + }, + { + "ph": "s", "id": 4, "pid": 2338706, "tid": 2338706, "ts": 6413850722816.003, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850722823.197, "dur": 3.050, + "args": { + "External id": 1429455,"Sequence number": 15348881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 15891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413850722862.497, "dur": 44613.302, + "args": { + "External id": 1429456,"Sequence number": 15348881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 15892 + } + }, + { + "ph": "s", "id": 3, "pid": 2338706, "tid": 2338706, "ts": 6413850722862.497, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413850722879.143, "dur": 31.741, + "args": { + "External id": 1429457,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413850722879.963, "dur": 30.684, + "args": { + "External id": 1429458,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850722881.408, "dur": 9.286, + "args": { + "External id": 1429459,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850722885.248, "dur": 4.885, + "args": { + "External id": 1429460,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722891.462, "dur": 18.648, + "args": { + "External id": 1429461,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 15897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850722929.552, "dur": 26.898, + "args": { + "External id": 1429462,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850722930.762, "dur": 6.286, + "args": { + "External id": 1429463,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 15899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722932.562, "dur": 4.030, + "args": { + "External id": 1429464,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722938.612, "dur": 17.581, + "args": { + "External id": 1429465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 15901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722940.431, "dur": 15.329, + "args": { + "External id": 1429466,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 15902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850722965.010, "dur": 45.938, + "args": { + "External id": 1429467,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850722965.881, "dur": 5.033, + "args": { + "External id": 1429468,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 15904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850722967.927, "dur": 2.737, + "args": { + "External id": 1429469,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722973.853, "dur": 36.846, + "args": { + "External id": 1429470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850722994.722, "dur": 15.320, + "args": { + "External id": 1429471,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 15907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413850723019.822, "dur": 20.775, + "args": { + "External id": 1429472,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 15908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850723021.574, "dur": 5.404, + "args": { + "External id": 1429473,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413850723027.762, "dur": 12.495, + "args": { + "External id": 1429474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 15910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850723028.444, "dur": 11.387, + "args": { + "External id": 1429475,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413850723045.875, "dur": 63.624, + "args": { + "External id": 1429476,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850723115.149, "dur": 65.867, + "args": { + "External id": 1429477,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 15913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850723120.542, "dur": 59.805, + "args": { + "External id": 1429478,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850723127.825, "dur": 1.244, + "args": { + "External id": 1429479,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 15915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850723130.458, "dur": 31.168, + "args": { + "External id": 1429480,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850723133.647, "dur": 27.706, + "args": { + "External id": 1429481,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 15917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850723137.848, "dur": 5.630, + "args": { + "External id": 1429482,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850723144.209, "dur": 16.710, + "args": { + "External id": 1429483,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 15919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413850723186.465, "dur": 37528.997, + "args": { + "External id": 1429484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413850723188.256, "dur": 37525.735, + "args": { + "External id": 1429485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 15921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850760733.529, "dur": 12.688, + "args": { + "External id": 1429486,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850760740.798, "dur": 1.437, + "args": { + "External id": 1429487,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850760756.494, "dur": 137.919, + "args": { + "External id": 1429488,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850760759.629, "dur": 8.468, + "args": { + "External id": 1429489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850760762.155, "dur": 4.682, + "args": { + "External id": 1429490,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850760765.417, "dur": 1.049, + "args": { + "External id": 1429491,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850760769.590, "dur": 123.896, + "args": { + "External id": 1429492,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850760772.586, "dur": 120.130, + "args": { + "External id": 1429493,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850760898.867, "dur": 4.649, + "args": { + "External id": 1429494,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850760901.203, "dur": 0.486, + "args": { + "External id": 1429495,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850760916.617, "dur": 3.973, + "args": { + "External id": 1429496,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850760933.657, "dur": 9.744, + "args": { + "External id": 1429497,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850760936.209, "dur": 6.856, + "args": { + "External id": 1429498,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850761180.436, "dur": 337.069, + "args": { + "External id": 1429499,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850761186.057, "dur": 5.880, + "args": { + "External id": 1429500,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850761197.742, "dur": 319.116, + "args": { + "External id": 1429501,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850761201.360, "dur": 0.523, + "args": { + "External id": 1429502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850761204.579, "dur": 39.452, + "args": { + "External id": 1429503,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850761245.944, "dur": 78.718, + "args": { + "External id": 1429504,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761321.472, "dur": 2.522, + "args": { + "External id": 1429505,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850761326.157, "dur": 29.743, + "args": { + "External id": 1429506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850761327.485, "dur": 2.163, + "args": { + "External id": 1429507,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850761331.211, "dur": 24.198, + "args": { + "External id": 1429508,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761335.721, "dur": 3.513, + "args": { + "External id": 1429509,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850761360.646, "dur": 25.774, + "args": { + "External id": 1429510,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761388.376, "dur": 18.143, + "args": { + "External id": 1429511,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850761410.294, "dur": 19.728, + "args": { + "External id": 1429512,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761431.892, "dur": 16.876, + "args": { + "External id": 1429513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850761451.282, "dur": 27.643, + "args": { + "External id": 1429514,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761453.840, "dur": 1.702, + "args": { + "External id": 1429515,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761457.680, "dur": 2.316, + "args": { + "External id": 1429516,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761483.426, "dur": 15.619, + "args": { + "External id": 1429517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761500.580, "dur": 14.678, + "args": { + "External id": 1429518,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850761528.261, "dur": 3.383, + "args": { + "External id": 1429519,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850761541.423, "dur": 6.184, + "args": { + "External id": 1429520,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761545.594, "dur": 0.817, + "args": { + "External id": 1429521,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850761656.058, "dur": 97.752, + "args": { + "External id": 1429522,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 15958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850761761.145, "dur": 10.820, + "args": { + "External id": 1429523,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761764.716, "dur": 4.406, + "args": { + "External id": 1429524,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761776.664, "dur": 33.372, + "args": { + "External id": 1429525,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 15961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850761816.736, "dur": 8.583, + "args": { + "External id": 1429526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 15962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850761818.903, "dur": 5.534, + "args": { + "External id": 1429527,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 15963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761822.316, "dur": 1.868, + "args": { + "External id": 1429528,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 15964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850761828.959, "dur": 58.372, + "args": { + "External id": 1429529,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850761830.394, "dur": 55.986, + "args": { + "External id": 1429530,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 15966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850761892.935, "dur": 20.149, + "args": { + "External id": 1429531,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 15967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850761922.957, "dur": 4.006, + "args": { + "External id": 1429532,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 15968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761925.351, "dur": 0.526, + "args": { + "External id": 1429533,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 15969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850761932.407, "dur": 75.611, + "args": { + "External id": 1429534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 15970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850761933.507, "dur": 3.551, + "args": { + "External id": 1429535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 15971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850761934.225, "dur": 2.158, + "args": { + "External id": 1429536,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 15972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850761935.583, "dur": 0.621, + "args": { + "External id": 1429537,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 15973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850761940.382, "dur": 67.036, + "args": { + "External id": 1429538,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850761941.023, "dur": 65.206, + "args": { + "External id": 1429539,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 15975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850762015.215, "dur": 5.059, + "args": { + "External id": 1429540,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 15976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762017.958, "dur": 0.705, + "args": { + "External id": 1429541,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 15977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850762028.692, "dur": 2.364, + "args": { + "External id": 1429542,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 15978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850762040.944, "dur": 10.799, + "args": { + "External id": 1429543,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 15979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850762045.881, "dur": 5.517, + "args": { + "External id": 1429544,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850762222.003, "dur": 217.108, + "args": { + "External id": 1429545,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850762226.637, "dur": 5.777, + "args": { + "External id": 1429546,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850762234.384, "dur": 204.160, + "args": { + "External id": 1429547,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 15983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850762236.150, "dur": 0.549, + "args": { + "External id": 1429548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850762238.372, "dur": 29.320, + "args": { + "External id": 1429549,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 15985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850762269.527, "dur": 4.980, + "args": { + "External id": 1429550,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 15986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762273.219, "dur": 0.854, + "args": { + "External id": 1429551,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 15987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850762277.992, "dur": 25.145, + "args": { + "External id": 1429552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850762279.094, "dur": 1.317, + "args": { + "External id": 1429553,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850762281.921, "dur": 20.886, + "args": { + "External id": 1429554,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 15990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762285.573, "dur": 2.874, + "args": { + "External id": 1429555,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850762304.934, "dur": 25.703, + "args": { + "External id": 1429556,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 15992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762332.400, "dur": 14.959, + "args": { + "External id": 1429557,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 15993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850762350.753, "dur": 14.816, + "args": { + "External id": 1429558,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 15994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762367.337, "dur": 14.666, + "args": { + "External id": 1429559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 15995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850762384.164, "dur": 25.010, + "args": { + "External id": 1429560,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 15996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762387.790, "dur": 1.648, + "args": { + "External id": 1429561,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 15997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762393.473, "dur": 0.775, + "args": { + "External id": 1429562,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 15998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762410.628, "dur": 13.336, + "args": { + "External id": 1429563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 15999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762425.244, "dur": 11.837, + "args": { + "External id": 1429564,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850762447.361, "dur": 3.087, + "args": { + "External id": 1429565,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850762461.146, "dur": 4.405, + "args": { + "External id": 1429566,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762463.895, "dur": 0.538, + "args": { + "External id": 1429567,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850762548.213, "dur": 72.870, + "args": { + "External id": 1429568,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850762627.582, "dur": 7.097, + "args": { + "External id": 1429569,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762632.729, "dur": 0.587, + "args": { + "External id": 1429570,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762636.764, "dur": 34.269, + "args": { + "External id": 1429571,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850762676.515, "dur": 8.723, + "args": { + "External id": 1429572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850762678.350, "dur": 6.035, + "args": { + "External id": 1429573,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762680.684, "dur": 3.446, + "args": { + "External id": 1429574,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850762700.744, "dur": 53.412, + "args": { + "External id": 1429575,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850762704.108, "dur": 49.205, + "args": { + "External id": 1429576,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850762758.779, "dur": 18.063, + "args": { + "External id": 1429577,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850762783.885, "dur": 4.252, + "args": { + "External id": 1429578,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762786.511, "dur": 0.548, + "args": { + "External id": 1429579,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850762793.445, "dur": 80.502, + "args": { + "External id": 1429580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850762794.430, "dur": 5.822, + "args": { + "External id": 1429581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850762795.274, "dur": 4.304, + "args": { + "External id": 1429582,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762798.971, "dur": 0.450, + "args": { + "External id": 1429583,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850762801.325, "dur": 72.107, + "args": { + "External id": 1429584,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850762802.192, "dur": 70.562, + "args": { + "External id": 1429585,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850762880.834, "dur": 3.831, + "args": { + "External id": 1429586,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850762882.952, "dur": 0.441, + "args": { + "External id": 1429587,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850762890.863, "dur": 1.609, + "args": { + "External id": 1429588,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850762901.561, "dur": 10.611, + "args": { + "External id": 1429589,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850762906.333, "dur": 5.456, + "args": { + "External id": 1429590,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850763039.613, "dur": 247.758, + "args": { + "External id": 1429591,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850763042.352, "dur": 3.591, + "args": { + "External id": 1429592,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850763047.800, "dur": 239.027, + "args": { + "External id": 1429593,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850763049.934, "dur": 0.500, + "args": { + "External id": 1429594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850763051.700, "dur": 70.527, + "args": { + "External id": 1429595,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850763125.601, "dur": 3.432, + "args": { + "External id": 1429596,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763127.777, "dur": 0.912, + "args": { + "External id": 1429597,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850763132.573, "dur": 26.530, + "args": { + "External id": 1429598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850763133.741, "dur": 1.907, + "args": { + "External id": 1429599,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850763137.284, "dur": 21.410, + "args": { + "External id": 1429600,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763142.104, "dur": 3.080, + "args": { + "External id": 1429601,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850763160.784, "dur": 21.791, + "args": { + "External id": 1429602,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763184.329, "dur": 14.869, + "args": { + "External id": 1429603,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850763202.184, "dur": 14.880, + "args": { + "External id": 1429604,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763218.742, "dur": 13.609, + "args": { + "External id": 1429605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850763234.567, "dur": 23.505, + "args": { + "External id": 1429606,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763239.715, "dur": 1.679, + "args": { + "External id": 1429607,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763243.252, "dur": 0.867, + "args": { + "External id": 1429608,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763259.969, "dur": 12.700, + "args": { + "External id": 1429609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763273.940, "dur": 11.625, + "args": { + "External id": 1429610,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850763297.280, "dur": 2.614, + "args": { + "External id": 1429611,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850763311.436, "dur": 4.269, + "args": { + "External id": 1429612,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763314.037, "dur": 0.559, + "args": { + "External id": 1429613,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850763400.110, "dur": 66.437, + "args": { + "External id": 1429614,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850763472.397, "dur": 5.222, + "args": { + "External id": 1429615,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763475.382, "dur": 1.020, + "args": { + "External id": 1429616,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763479.450, "dur": 29.469, + "args": { + "External id": 1429617,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850763514.302, "dur": 7.912, + "args": { + "External id": 1429618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850763516.022, "dur": 5.437, + "args": { + "External id": 1429619,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763520.434, "dur": 0.816, + "args": { + "External id": 1429620,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850763525.224, "dur": 51.745, + "args": { + "External id": 1429621,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850763526.211, "dur": 50.029, + "args": { + "External id": 1429622,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763581.432, "dur": 17.019, + "args": { + "External id": 1429623,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850763605.113, "dur": 9.111, + "args": { + "External id": 1429624,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763612.424, "dur": 0.581, + "args": { + "External id": 1429625,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850763619.195, "dur": 53.460, + "args": { + "External id": 1429626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850763622.353, "dur": 5.736, + "args": { + "External id": 1429627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850763623.620, "dur": 3.746, + "args": { + "External id": 1429628,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763624.758, "dur": 2.385, + "args": { + "External id": 1429629,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850763629.002, "dur": 43.101, + "args": { + "External id": 1429630,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850763629.620, "dur": 41.665, + "args": { + "External id": 1429631,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850763677.132, "dur": 3.778, + "args": { + "External id": 1429632,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763679.131, "dur": 0.435, + "args": { + "External id": 1429633,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850763689.333, "dur": 1.871, + "args": { + "External id": 1429634,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850763700.204, "dur": 7.239, + "args": { + "External id": 1429635,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850763702.547, "dur": 4.542, + "args": { + "External id": 1429636,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850763803.585, "dur": 221.451, + "args": { + "External id": 1429637,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850763806.035, "dur": 1.999, + "args": { + "External id": 1429638,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850763812.463, "dur": 211.951, + "args": { + "External id": 1429639,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850763813.904, "dur": 0.501, + "args": { + "External id": 1429640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850763818.305, "dur": 22.506, + "args": { + "External id": 1429641,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850763842.547, "dur": 4.817, + "args": { + "External id": 1429642,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763844.359, "dur": 2.754, + "args": { + "External id": 1429643,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850763848.233, "dur": 24.845, + "args": { + "External id": 1429644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850763849.442, "dur": 3.416, + "args": { + "External id": 1429645,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850763854.288, "dur": 18.460, + "args": { + "External id": 1429646,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763857.158, "dur": 2.239, + "args": { + "External id": 1429647,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850763874.365, "dur": 20.164, + "args": { + "External id": 1429648,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763896.253, "dur": 13.221, + "args": { + "External id": 1429649,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850763915.176, "dur": 13.479, + "args": { + "External id": 1429650,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763930.248, "dur": 12.776, + "args": { + "External id": 1429651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850763944.978, "dur": 21.364, + "args": { + "External id": 1429652,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763947.134, "dur": 1.610, + "args": { + "External id": 1429653,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850763950.686, "dur": 0.793, + "args": { + "External id": 1429654,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850763967.959, "dur": 35.491, + "args": { + "External id": 1429655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764007.940, "dur": 14.719, + "args": { + "External id": 1429656,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850764034.681, "dur": 2.633, + "args": { + "External id": 1429657,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850764046.984, "dur": 4.081, + "args": { + "External id": 1429658,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764049.377, "dur": 0.753, + "args": { + "External id": 1429659,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850764169.790, "dur": 67.554, + "args": { + "External id": 1429660,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850764243.693, "dur": 6.792, + "args": { + "External id": 1429661,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764247.325, "dur": 1.465, + "args": { + "External id": 1429662,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764252.364, "dur": 30.093, + "args": { + "External id": 1429663,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850764287.778, "dur": 10.678, + "args": { + "External id": 1429664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850764292.276, "dur": 5.295, + "args": { + "External id": 1429665,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764294.240, "dur": 3.078, + "args": { + "External id": 1429666,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850764301.560, "dur": 49.105, + "args": { + "External id": 1429667,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850764302.757, "dur": 46.982, + "args": { + "External id": 1429668,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764355.612, "dur": 17.771, + "args": { + "External id": 1429669,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850764380.040, "dur": 8.392, + "args": { + "External id": 1429670,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764384.765, "dur": 2.576, + "args": { + "External id": 1429671,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850764393.335, "dur": 53.198, + "args": { + "External id": 1429672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850764394.131, "dur": 3.764, + "args": { + "External id": 1429673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850764395.196, "dur": 2.016, + "args": { + "External id": 1429674,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764396.463, "dur": 0.580, + "args": { + "External id": 1429675,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850764398.766, "dur": 47.302, + "args": { + "External id": 1429676,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850764399.458, "dur": 45.735, + "args": { + "External id": 1429677,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850764451.089, "dur": 3.916, + "args": { + "External id": 1429678,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764453.252, "dur": 0.454, + "args": { + "External id": 1429679,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850764463.783, "dur": 1.875, + "args": { + "External id": 1429680,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850764474.895, "dur": 7.371, + "args": { + "External id": 1429681,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850764477.066, "dur": 4.912, + "args": { + "External id": 1429682,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850764585.157, "dur": 211.486, + "args": { + "External id": 1429683,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850764587.067, "dur": 2.312, + "args": { + "External id": 1429684,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850764595.170, "dur": 200.956, + "args": { + "External id": 1429685,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850764596.618, "dur": 0.632, + "args": { + "External id": 1429686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850764598.609, "dur": 25.170, + "args": { + "External id": 1429687,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850764625.575, "dur": 5.399, + "args": { + "External id": 1429688,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764627.961, "dur": 2.626, + "args": { + "External id": 1429689,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850764632.168, "dur": 26.933, + "args": { + "External id": 1429690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850764633.120, "dur": 4.205, + "args": { + "External id": 1429691,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850764638.521, "dur": 20.275, + "args": { + "External id": 1429692,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764641.201, "dur": 3.054, + "args": { + "External id": 1429693,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850764663.221, "dur": 23.041, + "args": { + "External id": 1429694,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764688.052, "dur": 17.033, + "args": { + "External id": 1429695,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850764708.335, "dur": 14.912, + "args": { + "External id": 1429696,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764724.737, "dur": 15.348, + "args": { + "External id": 1429697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850764742.306, "dur": 22.749, + "args": { + "External id": 1429698,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764744.789, "dur": 1.650, + "args": { + "External id": 1429699,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764748.514, "dur": 0.557, + "args": { + "External id": 1429700,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764769.434, "dur": 13.119, + "args": { + "External id": 1429701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764783.960, "dur": 10.907, + "args": { + "External id": 1429702,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850764803.915, "dur": 1.887, + "args": { + "External id": 1429703,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850764814.796, "dur": 3.934, + "args": { + "External id": 1429704,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764817.091, "dur": 0.693, + "args": { + "External id": 1429705,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850764900.810, "dur": 56.732, + "args": { + "External id": 1429706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850764963.106, "dur": 5.967, + "args": { + "External id": 1429707,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850764965.958, "dur": 1.797, + "args": { + "External id": 1429708,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850764973.091, "dur": 59.560, + "args": { + "External id": 1429709,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850765040.319, "dur": 6.459, + "args": { + "External id": 1429710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850765042.277, "dur": 3.601, + "args": { + "External id": 1429711,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765044.463, "dur": 1.213, + "args": { + "External id": 1429712,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850765050.123, "dur": 98.617, + "args": { + "External id": 1429713,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850765051.114, "dur": 96.096, + "args": { + "External id": 1429714,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765155.911, "dur": 19.313, + "args": { + "External id": 1429715,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850765184.844, "dur": 5.377, + "args": { + "External id": 1429716,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765187.969, "dur": 0.874, + "args": { + "External id": 1429717,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850765195.319, "dur": 55.932, + "args": { + "External id": 1429718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850765196.526, "dur": 6.806, + "args": { + "External id": 1429719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850765197.789, "dur": 4.824, + "args": { + "External id": 1429720,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765199.057, "dur": 3.408, + "args": { + "External id": 1429721,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850765206.294, "dur": 44.523, + "args": { + "External id": 1429722,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850765207.007, "dur": 42.949, + "args": { + "External id": 1429723,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850765255.949, "dur": 4.124, + "args": { + "External id": 1429724,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765258.026, "dur": 0.542, + "args": { + "External id": 1429725,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850765267.856, "dur": 1.713, + "args": { + "External id": 1429726,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850765278.652, "dur": 9.862, + "args": { + "External id": 1429727,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850765282.971, "dur": 5.234, + "args": { + "External id": 1429728,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850765391.828, "dur": 212.121, + "args": { + "External id": 1429729,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850765393.950, "dur": 3.796, + "args": { + "External id": 1429730,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850765399.380, "dur": 203.930, + "args": { + "External id": 1429731,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850765400.929, "dur": 0.679, + "args": { + "External id": 1429732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850765403.072, "dur": 24.254, + "args": { + "External id": 1429733,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850765428.958, "dur": 4.747, + "args": { + "External id": 1429734,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765432.684, "dur": 0.671, + "args": { + "External id": 1429735,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850765438.068, "dur": 24.471, + "args": { + "External id": 1429736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850765439.294, "dur": 1.743, + "args": { + "External id": 1429737,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850765442.449, "dur": 19.654, + "args": { + "External id": 1429738,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765445.383, "dur": 2.656, + "args": { + "External id": 1429739,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850765464.209, "dur": 27.067, + "args": { + "External id": 1429740,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765493.026, "dur": 15.121, + "args": { + "External id": 1429741,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850765511.119, "dur": 16.917, + "args": { + "External id": 1429742,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765529.482, "dur": 14.574, + "args": { + "External id": 1429743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850765545.955, "dur": 26.361, + "args": { + "External id": 1429744,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765548.207, "dur": 1.840, + "args": { + "External id": 1429745,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765554.076, "dur": 2.471, + "args": { + "External id": 1429746,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765573.910, "dur": 14.854, + "args": { + "External id": 1429747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765589.846, "dur": 12.090, + "args": { + "External id": 1429748,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850765611.484, "dur": 1.429, + "args": { + "External id": 1429749,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850765622.596, "dur": 3.747, + "args": { + "External id": 1429750,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765625.043, "dur": 0.473, + "args": { + "External id": 1429751,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850765697.283, "dur": 57.119, + "args": { + "External id": 1429752,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850765759.960, "dur": 7.202, + "args": { + "External id": 1429753,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765765.143, "dur": 0.836, + "args": { + "External id": 1429754,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765769.051, "dur": 26.303, + "args": { + "External id": 1429755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850765800.449, "dur": 6.083, + "args": { + "External id": 1429756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850765802.095, "dur": 3.655, + "args": { + "External id": 1429757,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765804.099, "dur": 1.428, + "args": { + "External id": 1429758,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850765809.387, "dur": 46.230, + "args": { + "External id": 1429759,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850765812.438, "dur": 42.323, + "args": { + "External id": 1429760,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850765859.752, "dur": 15.034, + "args": { + "External id": 1429761,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850765880.983, "dur": 3.833, + "args": { + "External id": 1429762,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765883.246, "dur": 0.551, + "args": { + "External id": 1429763,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850765888.906, "dur": 50.717, + "args": { + "External id": 1429764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850765889.709, "dur": 5.703, + "args": { + "External id": 1429765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850765890.632, "dur": 4.177, + "args": { + "External id": 1429766,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765894.008, "dur": 0.630, + "args": { + "External id": 1429767,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850765896.063, "dur": 42.965, + "args": { + "External id": 1429768,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850765896.839, "dur": 41.497, + "args": { + "External id": 1429769,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850765943.914, "dur": 3.648, + "args": { + "External id": 1429770,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850765945.886, "dur": 0.513, + "args": { + "External id": 1429771,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850765952.853, "dur": 1.298, + "args": { + "External id": 1429772,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850765962.044, "dur": 8.428, + "args": { + "External id": 1429773,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850765966.095, "dur": 4.064, + "args": { + "External id": 1429774,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850766128.156, "dur": 202.832, + "args": { + "External id": 1429775,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850766132.538, "dur": 4.443, + "args": { + "External id": 1429776,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850766138.673, "dur": 191.788, + "args": { + "External id": 1429777,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850766140.152, "dur": 0.478, + "args": { + "External id": 1429778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850766141.901, "dur": 23.754, + "args": { + "External id": 1429779,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850766167.188, "dur": 5.314, + "args": { + "External id": 1429780,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766171.171, "dur": 0.862, + "args": { + "External id": 1429781,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850766175.983, "dur": 22.752, + "args": { + "External id": 1429782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850766177.088, "dur": 1.502, + "args": { + "External id": 1429783,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850766179.915, "dur": 18.427, + "args": { + "External id": 1429784,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766183.199, "dur": 3.005, + "args": { + "External id": 1429785,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850766200.067, "dur": 24.061, + "args": { + "External id": 1429786,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766225.608, "dur": 14.661, + "args": { + "External id": 1429787,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850766243.342, "dur": 14.463, + "args": { + "External id": 1429788,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766259.170, "dur": 13.372, + "args": { + "External id": 1429789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850766274.802, "dur": 23.945, + "args": { + "External id": 1429790,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766281.018, "dur": 1.399, + "args": { + "External id": 1429791,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766284.250, "dur": 0.766, + "args": { + "External id": 1429792,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766300.514, "dur": 14.763, + "args": { + "External id": 1429793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766316.455, "dur": 12.657, + "args": { + "External id": 1429794,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850766338.794, "dur": 2.300, + "args": { + "External id": 1429795,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850766351.750, "dur": 4.570, + "args": { + "External id": 1429796,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766354.571, "dur": 0.592, + "args": { + "External id": 1429797,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850766435.344, "dur": 63.240, + "args": { + "External id": 1429798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850766504.244, "dur": 4.734, + "args": { + "External id": 1429799,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766506.864, "dur": 0.859, + "args": { + "External id": 1429800,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766510.561, "dur": 29.125, + "args": { + "External id": 1429801,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850766544.471, "dur": 9.347, + "args": { + "External id": 1429802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850766546.552, "dur": 6.458, + "args": { + "External id": 1429803,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766551.405, "dur": 1.437, + "args": { + "External id": 1429804,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850766556.690, "dur": 49.897, + "args": { + "External id": 1429805,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850766558.004, "dur": 47.778, + "args": { + "External id": 1429806,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766610.776, "dur": 16.572, + "args": { + "External id": 1429807,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850766633.932, "dur": 3.470, + "args": { + "External id": 1429808,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766635.886, "dur": 0.519, + "args": { + "External id": 1429809,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413850766642.470, "dur": 51.768, + "args": { + "External id": 1429810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 16246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850766645.784, "dur": 3.706, + "args": { + "External id": 1429811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850766646.825, "dur": 1.987, + "args": { + "External id": 1429812,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 16248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766648.112, "dur": 0.526, + "args": { + "External id": 1429813,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 16249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850766650.348, "dur": 43.470, + "args": { + "External id": 1429814,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850766651.028, "dur": 41.991, + "args": { + "External id": 1429815,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 16251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850766698.664, "dur": 3.871, + "args": { + "External id": 1429816,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766700.684, "dur": 0.554, + "args": { + "External id": 1429817,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850766711.772, "dur": 1.459, + "args": { + "External id": 1429818,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 16254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850766721.362, "dur": 6.686, + "args": { + "External id": 1429819,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 16255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850766723.413, "dur": 4.312, + "args": { + "External id": 1429820,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850766812.790, "dur": 211.477, + "args": { + "External id": 1429821,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850766816.281, "dur": 2.130, + "args": { + "External id": 1429822,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413850766822.047, "dur": 201.655, + "args": { + "External id": 1429823,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 16259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413850766823.028, "dur": 0.445, + "args": { + "External id": 1429824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413850766824.579, "dur": 19.930, + "args": { + "External id": 1429825,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 16261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413850766846.146, "dur": 4.356, + "args": { + "External id": 1429826,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 16262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766849.474, "dur": 0.784, + "args": { + "External id": 1429827,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 16263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850766851.693, "dur": 20.481, + "args": { + "External id": 1429828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413850766852.667, "dur": 1.370, + "args": { + "External id": 1429829,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413850766855.336, "dur": 16.457, + "args": { + "External id": 1429830,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 16266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766858.014, "dur": 2.070, + "args": { + "External id": 1429831,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413850766873.429, "dur": 21.324, + "args": { + "External id": 1429832,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766896.386, "dur": 15.093, + "args": { + "External id": 1429833,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413850766917.045, "dur": 13.823, + "args": { + "External id": 1429834,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 16270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766932.237, "dur": 12.768, + "args": { + "External id": 1429835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 16271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850766946.886, "dur": 20.755, + "args": { + "External id": 1429836,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 16272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766948.808, "dur": 1.742, + "args": { + "External id": 1429837,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850766952.136, "dur": 0.586, + "args": { + "External id": 1429838,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413850766969.019, "dur": 33.285, + "args": { + "External id": 1429839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 16275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850767006.898, "dur": 15.025, + "args": { + "External id": 1429840,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 16276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413850767033.083, "dur": 2.492, + "args": { + "External id": 1429841,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850767046.002, "dur": 4.276, + "args": { + "External id": 1429842,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 16278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850767048.538, "dur": 0.651, + "args": { + "External id": 1429843,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850767168.060, "dur": 65.440, + "args": { + "External id": 1429844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 16280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413850767239.658, "dur": 6.026, + "args": { + "External id": 1429845,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 16281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850767243.101, "dur": 0.903, + "args": { + "External id": 1429846,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 16282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850767247.038, "dur": 30.379, + "args": { + "External id": 1429847,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 16283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413850767282.648, "dur": 8.173, + "args": { + "External id": 1429848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 16284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413850767286.763, "dur": 3.280, + "args": { + "External id": 1429849,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 16285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850767288.553, "dur": 1.238, + "args": { + "External id": 1429850,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 16286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413850767293.425, "dur": 46.033, + "args": { + "External id": 1429851,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413850767294.625, "dur": 44.134, + "args": { + "External id": 1429852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 16288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850767343.572, "dur": 17.295, + "args": { + "External id": 1429853,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850767366.311, "dur": 26.164, + "args": { + "External id": 1429854,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 16290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413850767368.712, "dur": 23.292, + "args": { + "External id": 1429855,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 16291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850767373.907, "dur": 1.905, + "args": { + "External id": 1429856,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 16292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413850767398.409, "dur": 30.157, + "args": { + "External id": 1429857,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 16293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413850767403.118, "dur": 25.196, + "args": { + "External id": 1429858,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 16294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850767408.410, "dur": 3.989, + "args": { + "External id": 1429859,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413850767413.694, "dur": 14.059, + "args": { + "External id": 1429860,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 16296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850767440.780, "dur": 5.506, + "args": { + "External id": 1429861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 16297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850767443.025, "dur": 2.914, + "args": { + "External id": 1429862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 16298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850767447.668, "dur": 3.732, + "args": { + "External id": 1429863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413850767450.705, "dur": 0.562, + "args": { + "External id": 1429864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 16300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850767496.898, "dur": 25.201, + "args": { + "External id": 1429865,"Sequence number": 15348882, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 16301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413850767524.545, "dur": 16.549, + "args": { + "External id": 1429866,"Sequence number": 15348883, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 16302 + } + }, + { + "ph": "s", "id": 2, "pid": 2338706, "tid": 2338706, "ts": 6413850767524.545, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413850767661.665, "dur": 45.374, + "args": { + "External id": 1429867,"Record function id": 0, "Ev Idx": 16303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2338706, + "ts": 6413850767822.705, "dur": 38.518, + "args": { + "External id": 1429868,"Sequence number": 15348884, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 16304 + } + }, + { + "ph": "s", "id": 1, "pid": 2338706, "tid": 2338706, "ts": 6413850767822.705, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850767949.713, "dur": 83.870, + "args": { + "External id": 1429869,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 16305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413850767973.111, "dur": 35.824, + "args": { + "External id": 1429870,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 16306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413850768001.049, "dur": 6.818, + "args": { + "External id": 1429871,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413850768010.685, "dur": 22.390, + "args": { + "External id": 1429872,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 16308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2338706, + "ts": 6413852894471.947, "dur": 97.515, + "args": { + "External id": 1429873,"Sequence number": 15348885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 16309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2338706, + "ts": 6413852894586.355, "dur": 29.228, + "args": { + "External id": 1429874,"Sequence number": 15348886, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 16310 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 2338706, "tid": 2338706, + "ts": 6413852894668.391, "dur": 3688.390, + "args": { + "External id": 1429875,"Record function id": 0, "Ev Idx": 16311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852896693.782, "dur": 7.618, + "args": { + "External id": 1429876,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338706, "tid": 2338706, + "ts": 6413852896719.648, "dur": 9.555, + "args": { + "External id": 1429877,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 16313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852897367.766, "dur": 7.070, + "args": { + "External id": 1429878,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338706, "tid": 2338706, + "ts": 6413852897385.341, "dur": 5.159, + "args": { + "External id": 1429879,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 16315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852898186.340, "dur": 3.009, + "args": { + "External id": 1429880,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 2338706, "tid": 2338706, + "ts": 6413852898209.873, "dur": 3.721, + "args": { + "External id": 1429881,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[8, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 16317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852899024.590, "dur": 17.034, + "args": { + "External id": 1429882,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 16318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852899034.015, "dur": 2.834, + "args": { + "External id": 1429883,"Record function id": 0, "Concrete Inputs": ["", "[8, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 16319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852899043.702, "dur": 4.523, + "args": { + "External id": 1429884,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], []], "Ev Idx": 16320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852899045.889, "dur": 1.231, + "args": { + "External id": 1429885,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 16321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852899135.415, "dur": 13817.822, + "args": { + "External id": 1429886,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], [], []], "Ev Idx": 16322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852899145.229, "dur": 13806.013, + "args": { + "External id": 1429887,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 16323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852899151.612, "dur": 11.506, + "args": { + "External id": 1429888,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852899165.425, "dur": 13783.480, + "args": { + "External id": 1429889,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852899175.934, "dur": 0.581, + "args": { + "External id": 1429890,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 16326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338706, "tid": 2338706, + "ts": 6413852899179.649, "dur": 15.191, + "args": { + "External id": 1429891,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[8, 4096], [8, 4096]], "Ev Idx": 16327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338706, "tid": 2338706, + "ts": 6413852899186.565, "dur": 8.035, + "args": { + "External id": 1429892,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[8, 4096], [], []], "Ev Idx": 16328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852899193.355, "dur": 0.930, + "args": { + "External id": 1429893,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 16329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413852899196.701, "dur": 141.466, + "args": { + "External id": 1429894,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 16330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413852899201.760, "dur": 135.997, + "args": { + "External id": 1429895,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 16331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413852899203.969, "dur": 8.129, + "args": { + "External id": 1429896,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 16332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852899206.595, "dur": 4.921, + "args": { + "External id": 1429897,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852899213.244, "dur": 123.991, + "args": { + "External id": 1429898,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852899341.365, "dur": 13597.668, + "args": { + "External id": 1429899,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852913001.651, "dur": 475.955, + "args": { + "External id": 1429900,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 16336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852913006.122, "dur": 470.242, + "args": { + "External id": 1429901,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], []], "Ev Idx": 16337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852913015.964, "dur": 16.043, + "args": { + "External id": 1429902,"Record function id": 0, "Concrete Inputs": ["[8, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852913035.011, "dur": 437.511, + "args": { + "External id": 1429903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[8, 8192], [8, 8192], []], "Ev Idx": 16339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338706, "tid": 2338706, + "ts": 6413852913513.783, "dur": 65.384, + "args": { + "External id": 1429904,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852913521.304, "dur": 9.614, + "args": { + "External id": 1429905,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 2338706, "tid": 2338706, + "ts": 6413852913534.727, "dur": 43.870, + "args": { + "External id": 1429906,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 16342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413852913539.086, "dur": 8.666, + "args": { + "External id": 1429907,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 16343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 2338706, "tid": 2338706, + "ts": 6413852913594.513, "dur": 78.407, + "args": { + "External id": 1429908,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338706, "tid": 2338706, + "ts": 6413852913600.444, "dur": 7.298, + "args": { + "External id": 1429909,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 16345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852913603.878, "dur": 3.586, + "args": { + "External id": 1429910,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 16346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852913609.085, "dur": 3.965, + "args": { + "External id": 1429911,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413852913615.000, "dur": 1.994, + "args": { + "External id": 1429912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[8, 4096]], "Ev Idx": 16348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338706, "tid": 2338706, + "ts": 6413852913622.157, "dur": 6.202, + "args": { + "External id": 1429913,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 16349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852913627.439, "dur": 0.679, + "args": { + "External id": 1429914,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 16350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338706, "tid": 2338706, + "ts": 6413852913629.424, "dur": 4.701, + "args": { + "External id": 1429915,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 16351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852913632.442, "dur": 1.572, + "args": { + "External id": 1429916,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[8, 4096, 1], [], [], []], "Ev Idx": 16352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 2338706, "tid": 2338706, + "ts": 6413852913636.704, "dur": 4.054, + "args": { + "External id": 1429917,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [8, 1, 1, 4096]], "Ev Idx": 16353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 2338706, "tid": 2338706, + "ts": 6413852913637.982, "dur": 2.629, + "args": { + "External id": 1429918,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 16354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852913639.571, "dur": 0.895, + "args": { + "External id": 1429919,"Record function id": 0, "Concrete Inputs": ["", "[8, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 16355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852913641.995, "dur": 29.973, + "args": { + "External id": 1429920,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 4096, 4096, 1], [0, 4096, 4096, 1], []], "Input Dims": [[8, 1, 1, 4096], [8, 1, 1, 4096], []], "Ev Idx": 16356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852913683.097, "dur": 37.488, + "args": { + "External id": 1429921,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 16357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852913685.762, "dur": 34.572, + "args": { + "External id": 1429922,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], [], []], "Ev Idx": 16358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852913691.758, "dur": 5.523, + "args": { + "External id": 1429923,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852913698.334, "dur": 21.493, + "args": { + "External id": 1429924,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 16360 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413852913864.530, "dur": 285.152, + "args": { + "External id": 1429925,"Record function id": 0, "Ev Idx": 16361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338706, "tid": 2338706, + "ts": 6413852913969.959, "dur": 158.351, + "args": { + "External id": 1429926,"Record function id": 0, "Ev Idx": 16362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413852914162.094, "dur": 57.824, + "args": { + "External id": 1429927,"Record function id": 0, "Ev Idx": 16363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413852914230.240, "dur": 14578.810, + "args": { + "External id": 1429928,"Record function id": 0, "Ev Idx": 16364 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338706, "tid": 2338706, + "ts": 6413852914240.471, "dur": 2112.394, + "args": { + "External id": 1429929,"Record function id": 0, "Ev Idx": 16365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852914398.991, "dur": 16.579, + "args": { + "External id": 1429930,"Record function id": 0, "Concrete Inputs": ["[141824512]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852914437.791, "dur": 132.788, + "args": { + "External id": 1429931,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 16367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914446.158, "dur": 3.017, + "args": { + "External id": 1429932,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914452.538, "dur": 0.557, + "args": { + "External id": 1429933,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914455.147, "dur": 0.391, + "args": { + "External id": 1429934,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "16384512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914457.352, "dur": 1.275, + "args": { + "External id": 1429935,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "18481664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914460.392, "dur": 0.393, + "args": { + "External id": 1429936,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19005952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914462.223, "dur": 0.390, + "args": { + "External id": 1429937,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "19530240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914465.253, "dur": 0.392, + "args": { + "External id": 1429938,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914467.159, "dur": 2.713, + "args": { + "External id": 1429939,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "21627904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914471.675, "dur": 0.337, + "args": { + "External id": 1429940,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "28967936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914474.487, "dur": 0.313, + "args": { + "External id": 1429941,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "36307968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914476.095, "dur": 0.432, + "args": { + "External id": 1429942,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914477.996, "dur": 1.239, + "args": { + "External id": 1429943,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "43648512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914481.164, "dur": 0.365, + "args": { + "External id": 1429944,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "45745664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914483.331, "dur": 0.368, + "args": { + "External id": 1429945,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "46269952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914486.176, "dur": 0.336, + "args": { + "External id": 1429946,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "46794240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914487.953, "dur": 2.744, + "args": { + "External id": 1429947,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914492.873, "dur": 0.471, + "args": { + "External id": 1429948,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "48891904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914496.518, "dur": 0.554, + "args": { + "External id": 1429949,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "56231936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914498.495, "dur": 0.419, + "args": { + "External id": 1429950,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "63571968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914500.103, "dur": 1.358, + "args": { + "External id": 1429951,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914503.082, "dur": 0.395, + "args": { + "External id": 1429952,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "70912512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914504.892, "dur": 0.507, + "args": { + "External id": 1429953,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73009664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914507.812, "dur": 0.427, + "args": { + "External id": 1429954,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73533952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914510.296, "dur": 2.771, + "args": { + "External id": 1429955,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "74058240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914514.266, "dur": 0.381, + "args": { + "External id": 1429956,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914517.266, "dur": 0.418, + "args": { + "External id": 1429957,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "76155904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914519.359, "dur": 0.413, + "args": { + "External id": 1429958,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "83495936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914521.249, "dur": 1.406, + "args": { + "External id": 1429959,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "90835968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914523.706, "dur": 0.333, + "args": { + "External id": 1429960,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914525.345, "dur": 0.333, + "args": { + "External id": 1429961,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "98176512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914528.731, "dur": 0.361, + "args": { + "External id": 1429962,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100273664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914530.582, "dur": 2.530, + "args": { + "External id": 1429963,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100797952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914534.765, "dur": 0.289, + "args": { + "External id": 1429964,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "101322240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914537.541, "dur": 0.345, + "args": { + "External id": 1429965,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914539.196, "dur": 0.410, + "args": { + "External id": 1429966,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "103419904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914540.691, "dur": 1.542, + "args": { + "External id": 1429967,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "110759936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914543.867, "dur": 0.372, + "args": { + "External id": 1429968,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "118099968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914546.015, "dur": 0.372, + "args": { + "External id": 1429969,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914549.213, "dur": 0.348, + "args": { + "External id": 1429970,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "125440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852914607.791, "dur": 158.440, + "args": { + "External id": 1429971,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413852914867.987, "dur": 502.254, + "args": { + "External id": 1429972,"Record function id": 0, "Concrete Inputs": ["", "", "141824512", "8", "0", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 16408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852914889.636, "dur": 8.402, + "args": { + "External id": 1429973,"Record function id": 0, "Concrete Inputs": ["[1134596096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413852914905.351, "dur": 16.462, + "args": { + "External id": 1429974,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "141824512"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 16410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852914912.881, "dur": 8.364, + "args": { + "External id": 1429975,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "141824512", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[1134596096], [], [], [], []], "Ev Idx": 16411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914917.382, "dur": 0.763, + "args": { + "External id": 1429976,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[1134596096], [], [], []], "Ev Idx": 16412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852914931.691, "dur": 179.131, + "args": { + "External id": 1429977,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[141824512], [], []], "Ev Idx": 16413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914934.323, "dur": 0.470, + "args": { + "External id": 1429978,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914936.244, "dur": 1.505, + "args": { + "External id": 1429979,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "16384000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914939.151, "dur": 0.455, + "args": { + "External id": 1429980,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "16384512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914940.919, "dur": 0.307, + "args": { + "External id": 1429981,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "18481664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914944.213, "dur": 0.323, + "args": { + "External id": 1429982,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19005952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914945.887, "dur": 0.343, + "args": { + "External id": 1429983,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "19530240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914947.672, "dur": 2.800, + "args": { + "External id": 1429984,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "21627392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914953.260, "dur": 0.381, + "args": { + "External id": 1429985,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "21627904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914955.467, "dur": 0.379, + "args": { + "External id": 1429986,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "28967936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914957.337, "dur": 1.230, + "args": { + "External id": 1429987,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "36307968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914960.020, "dur": 0.390, + "args": { + "External id": 1429988,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "43648000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914961.743, "dur": 0.352, + "args": { + "External id": 1429989,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "43648512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914964.713, "dur": 0.405, + "args": { + "External id": 1429990,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "45745664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914966.867, "dur": 0.396, + "args": { + "External id": 1429991,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "46269952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914968.668, "dur": 2.524, + "args": { + "External id": 1429992,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "46794240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914973.634, "dur": 0.496, + "args": { + "External id": 1429993,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "48891392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914975.378, "dur": 18.389, + "args": { + "External id": 1429994,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "48891904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852914998.738, "dur": 1.748, + "args": { + "External id": 1429995,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "56231936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915001.907, "dur": 0.583, + "args": { + "External id": 1429996,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "63571968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915003.435, "dur": 0.327, + "args": { + "External id": 1429997,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "70912000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915006.123, "dur": 0.263, + "args": { + "External id": 1429998,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "70912512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915007.442, "dur": 0.371, + "args": { + "External id": 1429999,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73009664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915008.731, "dur": 2.649, + "args": { + "External id": 1430000,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "73533952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915013.653, "dur": 0.360, + "args": { + "External id": 1430001,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "74058240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915015.593, "dur": 0.355, + "args": { + "External id": 1430002,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "76155392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915017.071, "dur": 0.970, + "args": { + "External id": 1430003,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "76155904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915019.076, "dur": 0.373, + "args": { + "External id": 1430004,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "83495936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915020.983, "dur": 0.444, + "args": { + "External id": 1430005,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "90835968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915023.650, "dur": 0.397, + "args": { + "External id": 1430006,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "98176000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915025.234, "dur": 0.567, + "args": { + "External id": 1430007,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "98176512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915027.028, "dur": 3.229, + "args": { + "External id": 1430008,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100273664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915032.758, "dur": 0.449, + "args": { + "External id": 1430009,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "100797952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915033.946, "dur": 0.437, + "args": { + "External id": 1430010,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "101322240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915035.509, "dur": 1.412, + "args": { + "External id": 1430011,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "103419392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915037.793, "dur": 0.396, + "args": { + "External id": 1430012,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "103419904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915039.177, "dur": 0.542, + "args": { + "External id": 1430013,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "110759936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915041.982, "dur": 0.347, + "args": { + "External id": 1430014,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "118099968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915043.119, "dur": 0.275, + "args": { + "External id": 1430015,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "125440000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852915044.546, "dur": 2.747, + "args": { + "External id": 1430016,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "125440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[141824512], [], [], []], "Ev Idx": 16452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852915204.861, "dur": 141.592, + "args": { + "External id": 1436161,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413852915458.199, "dur": 582.046, + "args": { + "External id": 1436162,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[1134596096], [141824512], [], [], []], "Ev Idx": 16454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852915497.321, "dur": 533.493, + "args": { + "External id": 1436163,"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": 1134596096, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[141824512], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16455, "In msg nelems": 141824512 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413852915510.207, "dur": 509.813, + "args": { + "External id": 1436164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[141824512]], "Ev Idx": 16456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852916181.691, "dur": 6.630, + "args": { + "External id": 1436165,"Record function id": 0, "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": 16457, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 2338706, "tid": 2338706, + "ts": 6413852916380.555, "dur": 12120.136, + "args": { + "External id": 1436166,"Record function id": 0, "Ev Idx": 16458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916740.907, "dur": 9.722, + "args": { + "External id": 1436167,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[1134596096], []], "Ev Idx": 16459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916757.010, "dur": 2.409, + "args": { + "External id": 1436168,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 16460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916763.502, "dur": 2.084, + "args": { + "External id": 1436169,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916769.663, "dur": 1.500, + "args": { + "External id": 1436170,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916774.549, "dur": 1.397, + "args": { + "External id": 1436171,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916778.838, "dur": 1.843, + "args": { + "External id": 1436172,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916786.595, "dur": 1.738, + "args": { + "External id": 1436173,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916791.256, "dur": 5.970, + "args": { + "External id": 1436174,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916800.426, "dur": 1.430, + "args": { + "External id": 1436175,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916804.848, "dur": 1.460, + "args": { + "External id": 1436176,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916811.869, "dur": 1.311, + "args": { + "External id": 1436177,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916816.539, "dur": 1.220, + "args": { + "External id": 1436178,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916820.968, "dur": 1.186, + "args": { + "External id": 1436179,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916824.986, "dur": 1.375, + "args": { + "External id": 1436180,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916832.229, "dur": 1.157, + "args": { + "External id": 1436181,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916836.126, "dur": 5.572, + "args": { + "External id": 1436182,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916844.615, "dur": 1.151, + "args": { + "External id": 1436183,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916848.603, "dur": 1.933, + "args": { + "External id": 1436184,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916860.155, "dur": 1.431, + "args": { + "External id": 1436185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916865.360, "dur": 2.035, + "args": { + "External id": 1436186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916870.694, "dur": 1.364, + "args": { + "External id": 1436187,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916875.427, "dur": 1.490, + "args": { + "External id": 1436188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916882.306, "dur": 1.427, + "args": { + "External id": 1436189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916887.055, "dur": 5.197, + "args": { + "External id": 1436190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916895.765, "dur": 1.152, + "args": { + "External id": 1436191,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916899.747, "dur": 1.307, + "args": { + "External id": 1436192,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916906.667, "dur": 1.174, + "args": { + "External id": 1436193,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916910.354, "dur": 1.336, + "args": { + "External id": 1436194,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916914.887, "dur": 1.366, + "args": { + "External id": 1436195,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916919.268, "dur": 1.315, + "args": { + "External id": 1436196,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916926.182, "dur": 1.215, + "args": { + "External id": 1436197,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916930.307, "dur": 5.539, + "args": { + "External id": 1436198,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916938.898, "dur": 1.245, + "args": { + "External id": 1436199,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916943.106, "dur": 1.228, + "args": { + "External id": 1436200,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916950.385, "dur": 1.345, + "args": { + "External id": 1436201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916954.098, "dur": 1.096, + "args": { + "External id": 1436202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916957.795, "dur": 1.119, + "args": { + "External id": 1436203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916961.456, "dur": 1.107, + "args": { + "External id": 1436204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916967.967, "dur": 1.185, + "args": { + "External id": 1436205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852916971.941, "dur": 46.407, + "args": { + "External id": 1436206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[131072000], []], "Ev Idx": 16498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852917138.687, "dur": 11253.042, + "args": { + "External id": 1436207,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 16499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852917183.086, "dur": 11188.803, + "args": { + "External id": 1436208,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[141824512, 1], [], [], []], "Input Dims": [[8, 141824512], [], [], []], "Ev Idx": 16500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852917218.447, "dur": 23.048, + "args": { + "External id": 1436209,"Record function id": 0, "Concrete Inputs": ["[4384]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852917250.796, "dur": 11045.911, + "args": { + "External id": 1436210,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], [], []], "Ev Idx": 16502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852917254.541, "dur": 11040.840, + "args": { + "External id": 1436211,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4384], [], [], [], [], [], []], "Ev Idx": 16503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852917262.226, "dur": 10.183, + "args": { + "External id": 1436212,"Record function id": 0, "Concrete Inputs": ["[4384]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852917277.921, "dur": 11009.571, + "args": { + "External id": 1436213,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4384], [4384], []], "Ev Idx": 16505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413852928923.654, "dur": 47.482, + "args": { + "External id": 1436214,"Record function id": 0, "Ev Idx": 16506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338706, "tid": 2338706, + "ts": 6413852928974.020, "dur": 366.784, + "args": { + "External id": 1436215,"Record function id": 0, "Ev Idx": 16507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852929099.429, "dur": 229.487, + "args": { + "External id": 1436216,"Sequence number": 15348887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[4096, 1], [4096, 1]], "Input Dims": [[32000, 4096], [8, 4096]], "Ev Idx": 16508 + } + }, + { + "ph": "s", "id": 448, "pid": 2338706, "tid": 2338706, "ts": 6413852929099.429, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852929209.388, "dur": 71.111, + "args": { + "External id": 1436217,"kernel_hash": "cwt66mnkcya5wyvezkdac4cj5ntiugvh6bs2jikth6qdzhubcefg", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wt/cwt66mnkcya5wyvezkdac4cj5ntiugvh6bs2jikth6qdzhubcefg.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096], [32000, 4096], [8, 4096, 4096], []], "Ev Idx": 16509 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413852929419.982, "dur": 72.010, + "args": { + "External id": 1436218,"Record function id": 0, "Ev Idx": 16510 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338706, "tid": 2338706, + "ts": 6413852929506.263, "dur": 7968.852, + "args": { + "External id": 1436219,"Record function id": 0, "Ev Idx": 16511 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338706, "tid": 2338706, + "ts": 6413852929516.802, "dur": 1025.560, + "args": { + "External id": 1436220,"Record function id": 0, "Ev Idx": 16512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852929616.194, "dur": 11.973, + "args": { + "External id": 1436221,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852929646.701, "dur": 41.469, + "args": { + "External id": 1436222,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929655.786, "dur": 3.781, + "args": { + "External id": 1436223,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929661.872, "dur": 0.593, + "args": { + "External id": 1436224,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929663.725, "dur": 2.002, + "args": { + "External id": 1436225,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929666.802, "dur": 3.600, + "args": { + "External id": 1436226,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929671.445, "dur": 0.399, + "args": { + "External id": 1436227,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929674.859, "dur": 0.397, + "args": { + "External id": 1436228,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929676.657, "dur": 0.358, + "args": { + "External id": 1436229,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929678.050, "dur": 0.688, + "args": { + "External id": 1436230,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929680.929, "dur": 0.350, + "args": { + "External id": 1436231,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852929703.741, "dur": 61.372, + "args": { + "External id": 1436232,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413852929808.990, "dur": 143.401, + "args": { + "External id": 1436233,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852929824.444, "dur": 5.492, + "args": { + "External id": 1436234,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413852929837.406, "dur": 13.980, + "args": { + "External id": 1436235,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852929843.392, "dur": 7.507, + "args": { + "External id": 1436236,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929848.701, "dur": 0.721, + "args": { + "External id": 1436237,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852929858.564, "dur": 27.160, + "args": { + "External id": 1436238,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929860.237, "dur": 2.779, + "args": { + "External id": 1436239,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929864.884, "dur": 0.295, + "args": { + "External id": 1436240,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929867.387, "dur": 0.439, + "args": { + "External id": 1436241,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929868.959, "dur": 0.345, + "args": { + "External id": 1436242,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929870.144, "dur": 1.431, + "args": { + "External id": 1436243,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929872.949, "dur": 0.626, + "args": { + "External id": 1436244,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929874.570, "dur": 0.332, + "args": { + "External id": 1436245,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929877.121, "dur": 0.337, + "args": { + "External id": 1436246,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852929878.364, "dur": 2.847, + "args": { + "External id": 1436247,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852929898.371, "dur": 42.835, + "args": { + "External id": 1436248,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413852930044.891, "dur": 383.117, + "args": { + "External id": 1436249,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852930125.497, "dur": 296.381, + "args": { + "External id": 1436250,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16542, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413852930138.878, "dur": 276.658, + "args": { + "External id": 1436251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852930454.494, "dur": 2.915, + "args": { + "External id": 1436252,"Record function id": 0, "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": 16544, "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": 2338706, "tid": 2338706, + "ts": 6413852930567.615, "dur": 6610.850, + "args": { + "External id": 1436253,"Record function id": 0, "Ev Idx": 16545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930695.108, "dur": 8.434, + "args": { + "External id": 1436254,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930707.290, "dur": 1.646, + "args": { + "External id": 1436255,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930710.882, "dur": 1.097, + "args": { + "External id": 1436256,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930714.048, "dur": 0.983, + "args": { + "External id": 1436257,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930716.897, "dur": 1.149, + "args": { + "External id": 1436258,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930722.117, "dur": 0.966, + "args": { + "External id": 1436259,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930724.777, "dur": 1.005, + "args": { + "External id": 1436260,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930727.437, "dur": 5.209, + "args": { + "External id": 1436261,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930734.292, "dur": 1.205, + "args": { + "External id": 1436262,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852930739.580, "dur": 0.978, + "args": { + "External id": 1436263,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852930767.576, "dur": 6345.491, + "args": { + "External id": 1436264,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852930786.275, "dur": 6314.082, + "args": { + "External id": 1436265,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852930805.470, "dur": 17.612, + "args": { + "External id": 1436266,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852930829.925, "dur": 6186.060, + "args": { + "External id": 1436267,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852930832.711, "dur": 6182.203, + "args": { + "External id": 1436268,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852930838.010, "dur": 5.662, + "args": { + "External id": 1436269,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852930845.554, "dur": 6164.512, + "args": { + "External id": 1436270,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852937404.206, "dur": 41.348, + "args": { + "External id": 1436271,"Sequence number": 15348888, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16563 + } + }, + { + "ph": "s", "id": 447, "pid": 2338706, "tid": 2338706, "ts": 6413852937404.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413852937426.123, "dur": 13.683, + "args": { + "External id": 1436272,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852937432.145, "dur": 7.410, + "args": { + "External id": 1436273,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413852937527.287, "dur": 106.290, + "args": { + "External id": 1436274,"Record function id": 0, "Ev Idx": 16566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413852937635.036, "dur": 1402.723, + "args": { + "External id": 1436275,"Record function id": 0, "Ev Idx": 16567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852937680.269, "dur": 1339.486, + "args": { + "External id": 1436276,"Sequence number": 15348889, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16568 + } + }, + { + "ph": "s", "id": 446, "pid": 2338706, "tid": 2338706, "ts": 6413852937680.269, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852937773.677, "dur": 60.361, + "args": { + "External id": 1436277,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852937852.271, "dur": 123.219, + "args": { + "External id": 1436278,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852938012.938, "dur": 95.861, + "args": { + "External id": 1436279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852938126.086, "dur": 43.464, + "args": { + "External id": 1436280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413852938206.622, "dur": 36.304, + "args": { + "External id": 1436281,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413852938269.317, "dur": 24.628, + "args": { + "External id": 1436282,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413852938320.516, "dur": 167.175, + "args": { + "External id": 1436283,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413852938384.951, "dur": 20.284, + "args": { + "External id": 1436284,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852938392.052, "dur": 11.093, + "args": { + "External id": 1436285,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852938408.532, "dur": 4.568, + "args": { + "External id": 1436286,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852938414.793, "dur": 1.212, + "args": { + "External id": 1436287,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852938418.888, "dur": 4.304, + "args": { + "External id": 1436288,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852938501.000, "dur": 63.253, + "args": { + "External id": 1436289,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413852938599.215, "dur": 39.079, + "args": { + "External id": 1436290,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852938648.491, "dur": 51.875, + "args": { + "External id": 1436291,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852938710.451, "dur": 40.257, + "args": { + "External id": 1436292,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852938777.775, "dur": 32.487, + "args": { + "External id": 1436293,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852938818.655, "dur": 43.855, + "args": { + "External id": 1436294,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413852938885.646, "dur": 23.790, + "args": { + "External id": 1436295,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16587 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 2338706, "tid": 2338706, + "ts": 6413852939159.965, "dur": 106.798, + "args": { + "External id": 1436296,"Record function id": 0, "Ev Idx": 16588 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413852939357.647, "dur": 55.738, + "args": { + "External id": 1436297,"Record function id": 0, "Ev Idx": 16589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338706, "tid": 2338706, + "ts": 6413852939424.521, "dur": 27095.787, + "args": { + "External id": 1436298,"Record function id": 0, "Ev Idx": 16590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338706, "tid": 2338706, + "ts": 6413852939434.778, "dur": 1178.851, + "args": { + "External id": 1436299,"Record function id": 0, "Ev Idx": 16591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852939534.685, "dur": 11.931, + "args": { + "External id": 1436300,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852939562.557, "dur": 42.145, + "args": { + "External id": 1436301,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939569.247, "dur": 3.865, + "args": { + "External id": 1436302,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939575.340, "dur": 0.719, + "args": { + "External id": 1436303,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939577.322, "dur": 0.690, + "args": { + "External id": 1436304,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939581.278, "dur": 0.394, + "args": { + "External id": 1436305,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939582.892, "dur": 0.599, + "args": { + "External id": 1436306,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939584.654, "dur": 0.665, + "args": { + "External id": 1436307,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939588.472, "dur": 3.770, + "args": { + "External id": 1436308,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939593.936, "dur": 0.399, + "args": { + "External id": 1436309,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939595.628, "dur": 2.330, + "args": { + "External id": 1436310,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852939626.161, "dur": 68.641, + "args": { + "External id": 1436311,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413852939734.200, "dur": 139.018, + "args": { + "External id": 1436312,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852939747.279, "dur": 6.071, + "args": { + "External id": 1436313,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413852939759.962, "dur": 11.769, + "args": { + "External id": 1436314,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852939765.277, "dur": 5.769, + "args": { + "External id": 1436315,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939768.886, "dur": 0.728, + "args": { + "External id": 1436316,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852939779.460, "dur": 29.196, + "args": { + "External id": 1436317,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939781.773, "dur": 0.791, + "args": { + "External id": 1436318,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939784.127, "dur": 2.085, + "args": { + "External id": 1436319,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939787.874, "dur": 0.678, + "args": { + "External id": 1436320,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939789.571, "dur": 2.827, + "args": { + "External id": 1436321,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939795.097, "dur": 0.333, + "args": { + "External id": 1436322,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939796.469, "dur": 0.618, + "args": { + "External id": 1436323,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939798.017, "dur": 0.534, + "args": { + "External id": 1436324,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939801.417, "dur": 0.447, + "args": { + "External id": 1436325,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852939802.931, "dur": 0.373, + "args": { + "External id": 1436326,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852939824.646, "dur": 39.339, + "args": { + "External id": 1436327,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413852939936.442, "dur": 542.381, + "args": { + "External id": 1436328,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852939973.774, "dur": 497.642, + "args": { + "External id": 1436329,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16621, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413852940009.034, "dur": 454.284, + "args": { + "External id": 1436330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852940514.613, "dur": 3.370, + "args": { + "External id": 1436331,"Record function id": 0, "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": 16623, "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": 2338706, "tid": 2338706, + "ts": 6413852940639.186, "dur": 25590.045, + "args": { + "External id": 1436332,"Record function id": 0, "Ev Idx": 16624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940769.105, "dur": 7.608, + "args": { + "External id": 1436333,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940780.558, "dur": 1.210, + "args": { + "External id": 1436334,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940783.949, "dur": 4.328, + "args": { + "External id": 1436335,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940790.314, "dur": 1.138, + "args": { + "External id": 1436336,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940793.078, "dur": 1.332, + "args": { + "External id": 1436337,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940798.343, "dur": 1.086, + "args": { + "External id": 1436338,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940801.298, "dur": 1.165, + "args": { + "External id": 1436339,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940804.154, "dur": 2.686, + "args": { + "External id": 1436340,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940808.483, "dur": 1.008, + "args": { + "External id": 1436341,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852940813.821, "dur": 0.930, + "args": { + "External id": 1436342,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852940835.543, "dur": 25316.836, + "args": { + "External id": 1436343,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852940854.755, "dur": 25283.544, + "args": { + "External id": 1436344,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852940873.972, "dur": 19.207, + "args": { + "External id": 1436345,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852940897.605, "dur": 25153.248, + "args": { + "External id": 1436346,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852940901.070, "dur": 25148.639, + "args": { + "External id": 1436347,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852940907.528, "dur": 6.360, + "args": { + "External id": 1436348,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852940915.988, "dur": 25127.996, + "args": { + "External id": 1436349,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852966444.355, "dur": 45.054, + "args": { + "External id": 1436350,"Sequence number": 15348890, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16642 + } + }, + { + "ph": "s", "id": 445, "pid": 2338706, "tid": 2338706, "ts": 6413852966444.355, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413852966465.615, "dur": 18.089, + "args": { + "External id": 1436351,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852966475.502, "dur": 7.846, + "args": { + "External id": 1436352,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413852966573.263, "dur": 89.361, + "args": { + "External id": 1436353,"Record function id": 0, "Ev Idx": 16645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413852966664.313, "dur": 1349.476, + "args": { + "External id": 1436354,"Record function id": 0, "Ev Idx": 16646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852966709.157, "dur": 1286.389, + "args": { + "External id": 1436355,"Sequence number": 15348891, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16647 + } + }, + { + "ph": "s", "id": 444, "pid": 2338706, "tid": 2338706, "ts": 6413852966709.157, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852966801.751, "dur": 60.323, + "args": { + "External id": 1436356,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852966878.057, "dur": 132.288, + "args": { + "External id": 1436357,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852967033.148, "dur": 95.890, + "args": { + "External id": 1436358,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852967143.422, "dur": 38.310, + "args": { + "External id": 1436359,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413852967217.315, "dur": 33.221, + "args": { + "External id": 1436360,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413852967276.104, "dur": 20.174, + "args": { + "External id": 1436361,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413852967322.667, "dur": 162.828, + "args": { + "External id": 1436362,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413852967383.353, "dur": 17.952, + "args": { + "External id": 1436363,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852967390.557, "dur": 9.546, + "args": { + "External id": 1436364,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852967405.364, "dur": 4.885, + "args": { + "External id": 1436365,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852967411.795, "dur": 1.259, + "args": { + "External id": 1436366,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852967418.037, "dur": 5.743, + "args": { + "External id": 1436367,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852967498.278, "dur": 59.840, + "args": { + "External id": 1436368,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413852967595.572, "dur": 34.498, + "args": { + "External id": 1436369,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852967641.261, "dur": 49.822, + "args": { + "External id": 1436370,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852967698.611, "dur": 41.775, + "args": { + "External id": 1436371,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852967765.233, "dur": 35.964, + "args": { + "External id": 1436372,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852967807.466, "dur": 44.768, + "args": { + "External id": 1436373,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413852967873.752, "dur": 23.771, + "args": { + "External id": 1436374,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 2338706, "tid": 2338706, + "ts": 6413852968136.005, "dur": 96.998, + "args": { + "External id": 1436375,"Record function id": 0, "Ev Idx": 16667 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413852968325.575, "dur": 56.289, + "args": { + "External id": 1436376,"Record function id": 0, "Ev Idx": 16668 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338706, "tid": 2338706, + "ts": 6413852968392.460, "dur": 28431.526, + "args": { + "External id": 1436377,"Record function id": 0, "Ev Idx": 16669 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338706, "tid": 2338706, + "ts": 6413852968403.842, "dur": 1085.911, + "args": { + "External id": 1436378,"Record function id": 0, "Ev Idx": 16670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852968503.425, "dur": 10.776, + "args": { + "External id": 1436379,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852968529.873, "dur": 39.777, + "args": { + "External id": 1436380,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968536.271, "dur": 2.558, + "args": { + "External id": 1436381,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968543.274, "dur": 0.559, + "args": { + "External id": 1436382,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968544.970, "dur": 0.685, + "args": { + "External id": 1436383,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968547.167, "dur": 0.709, + "args": { + "External id": 1436384,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968550.584, "dur": 0.630, + "args": { + "External id": 1436385,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968552.212, "dur": 1.008, + "args": { + "External id": 1436386,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968554.189, "dur": 4.392, + "args": { + "External id": 1436387,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968559.747, "dur": 0.573, + "args": { + "External id": 1436388,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968561.480, "dur": 0.560, + "args": { + "External id": 1436389,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852968582.836, "dur": 63.577, + "args": { + "External id": 1436390,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413852968684.755, "dur": 135.485, + "args": { + "External id": 1436391,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852968697.796, "dur": 4.852, + "args": { + "External id": 1436392,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413852968708.885, "dur": 12.382, + "args": { + "External id": 1436393,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852968714.224, "dur": 6.542, + "args": { + "External id": 1436394,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968718.573, "dur": 0.719, + "args": { + "External id": 1436395,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852968729.340, "dur": 29.006, + "args": { + "External id": 1436396,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968731.560, "dur": 1.393, + "args": { + "External id": 1436397,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968734.346, "dur": 0.522, + "args": { + "External id": 1436398,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968735.982, "dur": 0.398, + "args": { + "External id": 1436399,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968739.209, "dur": 2.925, + "args": { + "External id": 1436400,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968743.212, "dur": 0.503, + "args": { + "External id": 1436401,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968744.822, "dur": 0.582, + "args": { + "External id": 1436402,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968747.543, "dur": 0.619, + "args": { + "External id": 1436403,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968749.565, "dur": 0.353, + "args": { + "External id": 1436404,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852968750.768, "dur": 1.597, + "args": { + "External id": 1436405,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852968775.242, "dur": 34.985, + "args": { + "External id": 1436406,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413852968881.522, "dur": 488.525, + "args": { + "External id": 1436407,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852968916.421, "dur": 447.197, + "args": { + "External id": 1436408,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16700, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413852968929.809, "dur": 426.799, + "args": { + "External id": 1436409,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852969400.515, "dur": 3.224, + "args": { + "External id": 1436410,"Record function id": 0, "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": 16702, "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": 2338706, "tid": 2338706, + "ts": 6413852969514.803, "dur": 27034.030, + "args": { + "External id": 1436411,"Record function id": 0, "Ev Idx": 16703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969643.125, "dur": 7.526, + "args": { + "External id": 1436412,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969654.657, "dur": 1.367, + "args": { + "External id": 1436413,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969658.144, "dur": 3.886, + "args": { + "External id": 1436414,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969664.148, "dur": 1.385, + "args": { + "External id": 1436415,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969667.170, "dur": 1.232, + "args": { + "External id": 1436416,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969669.874, "dur": 1.206, + "args": { + "External id": 1436417,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969675.137, "dur": 1.335, + "args": { + "External id": 1436418,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969678.211, "dur": 3.057, + "args": { + "External id": 1436419,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969683.027, "dur": 0.975, + "args": { + "External id": 1436420,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852969685.648, "dur": 1.312, + "args": { + "External id": 1436421,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852969709.466, "dur": 26756.859, + "args": { + "External id": 1436422,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852969727.175, "dur": 26722.441, + "args": { + "External id": 1436423,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852969745.627, "dur": 18.325, + "args": { + "External id": 1436424,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413852969767.882, "dur": 26621.313, + "args": { + "External id": 1436425,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413852969770.883, "dur": 26616.628, + "args": { + "External id": 1436426,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852969776.545, "dur": 6.201, + "args": { + "External id": 1436427,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852969784.533, "dur": 26594.641, + "args": { + "External id": 1436428,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852996744.234, "dur": 48.587, + "args": { + "External id": 1436429,"Sequence number": 15348892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16721 + } + }, + { + "ph": "s", "id": 443, "pid": 2338706, "tid": 2338706, "ts": 6413852996744.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413852996769.002, "dur": 16.694, + "args": { + "External id": 1436430,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852996776.482, "dur": 8.892, + "args": { + "External id": 1436431,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413852996873.232, "dur": 85.433, + "args": { + "External id": 1436432,"Record function id": 0, "Ev Idx": 16724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413852996960.559, "dur": 1405.913, + "args": { + "External id": 1436433,"Record function id": 0, "Ev Idx": 16725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413852997029.038, "dur": 1320.312, + "args": { + "External id": 1436434,"Sequence number": 15348893, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16726 + } + }, + { + "ph": "s", "id": 442, "pid": 2338706, "tid": 2338706, "ts": 6413852997029.038, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852997175.483, "dur": 67.937, + "args": { + "External id": 1436435,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852997263.666, "dur": 119.384, + "args": { + "External id": 1436436,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852997399.669, "dur": 43.215, + "args": { + "External id": 1436437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852997452.919, "dur": 36.562, + "args": { + "External id": 1436438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413852997520.587, "dur": 31.878, + "args": { + "External id": 1436439,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413852997575.133, "dur": 21.846, + "args": { + "External id": 1436440,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413852997624.580, "dur": 157.309, + "args": { + "External id": 1436441,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413852997683.348, "dur": 14.527, + "args": { + "External id": 1436442,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852997690.932, "dur": 6.067, + "args": { + "External id": 1436443,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852997701.000, "dur": 5.946, + "args": { + "External id": 1436444,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852997708.333, "dur": 1.527, + "args": { + "External id": 1436445,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852997712.686, "dur": 7.987, + "args": { + "External id": 1436446,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852997794.387, "dur": 54.577, + "args": { + "External id": 1436447,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413852997888.234, "dur": 33.792, + "args": { + "External id": 1436448,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852997932.557, "dur": 70.579, + "args": { + "External id": 1436449,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852998016.357, "dur": 86.948, + "args": { + "External id": 1436450,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413852998135.585, "dur": 35.060, + "args": { + "External id": 1436451,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413852998179.846, "dur": 45.891, + "args": { + "External id": 1436452,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413852998247.304, "dur": 20.478, + "args": { + "External id": 1436453,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 2338706, "tid": 2338706, + "ts": 6413852998441.933, "dur": 100.068, + "args": { + "External id": 1436454,"Record function id": 0, "Ev Idx": 16746 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413852998630.131, "dur": 56.008, + "args": { + "External id": 1436455,"Record function id": 0, "Ev Idx": 16747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338706, "tid": 2338706, + "ts": 6413852998696.856, "dur": 29659.755, + "args": { + "External id": 1436456,"Record function id": 0, "Ev Idx": 16748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338706, "tid": 2338706, + "ts": 6413852998706.419, "dur": 1079.044, + "args": { + "External id": 1436457,"Record function id": 0, "Ev Idx": 16749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852998804.230, "dur": 10.270, + "args": { + "External id": 1436458,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852998830.330, "dur": 40.071, + "args": { + "External id": 1436459,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998836.411, "dur": 2.548, + "args": { + "External id": 1436460,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998842.884, "dur": 0.462, + "args": { + "External id": 1436461,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998845.170, "dur": 0.461, + "args": { + "External id": 1436462,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998847.065, "dur": 0.732, + "args": { + "External id": 1436463,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998850.092, "dur": 0.645, + "args": { + "External id": 1436464,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998852.037, "dur": 0.709, + "args": { + "External id": 1436465,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998854.103, "dur": 4.136, + "args": { + "External id": 1436466,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998859.569, "dur": 0.515, + "args": { + "External id": 1436467,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852998861.305, "dur": 0.805, + "args": { + "External id": 1436468,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852998883.786, "dur": 60.356, + "args": { + "External id": 1436469,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413852999004.351, "dur": 195.321, + "args": { + "External id": 1436470,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413852999019.612, "dur": 6.416, + "args": { + "External id": 1436471,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413852999032.578, "dur": 12.981, + "args": { + "External id": 1436472,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413852999037.995, "dur": 7.018, + "args": { + "External id": 1436473,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999042.162, "dur": 1.055, + "args": { + "External id": 1436474,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413852999094.884, "dur": 32.142, + "args": { + "External id": 1436475,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999098.960, "dur": 2.232, + "args": { + "External id": 1436476,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999102.979, "dur": 0.375, + "args": { + "External id": 1436477,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999104.775, "dur": 0.416, + "args": { + "External id": 1436478,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999107.874, "dur": 2.711, + "args": { + "External id": 1436479,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999112.265, "dur": 0.313, + "args": { + "External id": 1436480,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999113.787, "dur": 0.400, + "args": { + "External id": 1436481,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999115.841, "dur": 0.409, + "args": { + "External id": 1436482,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999117.310, "dur": 0.414, + "args": { + "External id": 1436483,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413852999119.052, "dur": 1.409, + "args": { + "External id": 1436484,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413852999145.794, "dur": 42.902, + "args": { + "External id": 1436485,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413852999269.031, "dur": 407.822, + "args": { + "External id": 1436486,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852999307.730, "dur": 363.432, + "args": { + "External id": 1436487,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16779, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413852999319.681, "dur": 345.210, + "args": { + "External id": 1436488,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413852999702.811, "dur": 2.841, + "args": { + "External id": 1436489,"Record function id": 0, "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": 16781, "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": 2338706, "tid": 2338706, + "ts": 6413852999810.281, "dur": 28286.927, + "args": { + "External id": 1436490,"Record function id": 0, "Ev Idx": 16782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999930.612, "dur": 6.522, + "args": { + "External id": 1436491,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999940.800, "dur": 1.651, + "args": { + "External id": 1436492,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999944.449, "dur": 4.360, + "args": { + "External id": 1436493,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999950.932, "dur": 1.313, + "args": { + "External id": 1436494,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999954.266, "dur": 1.207, + "args": { + "External id": 1436495,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999957.486, "dur": 1.253, + "args": { + "External id": 1436496,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999963.187, "dur": 0.890, + "args": { + "External id": 1436497,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999966.175, "dur": 3.130, + "args": { + "External id": 1436498,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999971.273, "dur": 0.842, + "args": { + "External id": 1436499,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413852999973.710, "dur": 1.182, + "args": { + "External id": 1436500,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853000021.939, "dur": 27986.375, + "args": { + "External id": 1436501,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853000040.956, "dur": 27956.373, + "args": { + "External id": 1436502,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853000100.275, "dur": 21.208, + "args": { + "External id": 1436503,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853000126.034, "dur": 27815.723, + "args": { + "External id": 1436504,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853000129.311, "dur": 27811.693, + "args": { + "External id": 1436505,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853000134.766, "dur": 6.562, + "args": { + "External id": 1436506,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853000143.414, "dur": 27793.801, + "args": { + "External id": 1436507,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853028285.089, "dur": 41.730, + "args": { + "External id": 1436508,"Sequence number": 15348894, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16800 + } + }, + { + "ph": "s", "id": 441, "pid": 2338706, "tid": 2338706, "ts": 6413853028285.089, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853028307.479, "dur": 13.546, + "args": { + "External id": 1436509,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853028313.299, "dur": 7.416, + "args": { + "External id": 1436510,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853028405.420, "dur": 88.101, + "args": { + "External id": 1436511,"Record function id": 0, "Ev Idx": 16803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853028495.131, "dur": 1327.072, + "args": { + "External id": 1436512,"Record function id": 0, "Ev Idx": 16804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853028541.409, "dur": 1264.687, + "args": { + "External id": 1436513,"Sequence number": 15348895, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16805 + } + }, + { + "ph": "s", "id": 440, "pid": 2338706, "tid": 2338706, "ts": 6413853028541.409, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853028628.820, "dur": 62.270, + "args": { + "External id": 1436514,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853028713.166, "dur": 118.684, + "args": { + "External id": 1436515,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853028846.679, "dur": 45.064, + "args": { + "External id": 1436516,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853028901.798, "dur": 34.616, + "args": { + "External id": 1436517,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853028969.791, "dur": 55.312, + "args": { + "External id": 1436518,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853029089.486, "dur": 27.204, + "args": { + "External id": 1436519,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853029146.344, "dur": 159.183, + "args": { + "External id": 1436520,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853029204.953, "dur": 16.112, + "args": { + "External id": 1436521,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853029212.292, "dur": 7.752, + "args": { + "External id": 1436522,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853029225.246, "dur": 4.906, + "args": { + "External id": 1436523,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853029231.493, "dur": 1.511, + "args": { + "External id": 1436524,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853029235.996, "dur": 6.176, + "args": { + "External id": 1436525,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853029320.101, "dur": 69.153, + "args": { + "External id": 1436526,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853029429.991, "dur": 34.534, + "args": { + "External id": 1436527,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853029476.694, "dur": 48.676, + "args": { + "External id": 1436528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853029534.947, "dur": 40.154, + "args": { + "External id": 1436529,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853029600.217, "dur": 31.890, + "args": { + "External id": 1436530,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853029640.052, "dur": 45.309, + "args": { + "External id": 1436531,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853029706.765, "dur": 23.686, + "args": { + "External id": 1436532,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16824 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 2338706, "tid": 2338706, + "ts": 6413853029895.249, "dur": 113.532, + "args": { + "External id": 1436533,"Record function id": 0, "Ev Idx": 16825 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853030144.524, "dur": 57.576, + "args": { + "External id": 1436534,"Record function id": 0, "Ev Idx": 16826 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338706, "tid": 2338706, + "ts": 6413853030213.423, "dur": 28681.188, + "args": { + "External id": 1436535,"Record function id": 0, "Ev Idx": 16827 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338706, "tid": 2338706, + "ts": 6413853030224.076, "dur": 1059.188, + "args": { + "External id": 1436536,"Record function id": 0, "Ev Idx": 16828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853030322.197, "dur": 11.955, + "args": { + "External id": 1436537,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853030351.661, "dur": 38.665, + "args": { + "External id": 1436538,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030357.768, "dur": 2.649, + "args": { + "External id": 1436539,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030364.241, "dur": 0.695, + "args": { + "External id": 1436540,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030366.337, "dur": 0.376, + "args": { + "External id": 1436541,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030367.947, "dur": 0.656, + "args": { + "External id": 1436542,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030371.197, "dur": 0.744, + "args": { + "External id": 1436543,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030373.182, "dur": 0.525, + "args": { + "External id": 1436544,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030374.657, "dur": 3.916, + "args": { + "External id": 1436545,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030379.856, "dur": 0.677, + "args": { + "External id": 1436546,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030381.631, "dur": 0.504, + "args": { + "External id": 1436547,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853030404.033, "dur": 65.095, + "args": { + "External id": 1436548,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853030511.298, "dur": 134.298, + "args": { + "External id": 1436549,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853030524.425, "dur": 5.965, + "args": { + "External id": 1436550,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853030536.985, "dur": 12.086, + "args": { + "External id": 1436551,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853030542.055, "dur": 6.508, + "args": { + "External id": 1436552,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030546.138, "dur": 0.932, + "args": { + "External id": 1436553,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853030556.811, "dur": 28.091, + "args": { + "External id": 1436554,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030558.845, "dur": 0.661, + "args": { + "External id": 1436555,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030561.131, "dur": 1.785, + "args": { + "External id": 1436556,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030564.136, "dur": 0.303, + "args": { + "External id": 1436557,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030565.667, "dur": 3.294, + "args": { + "External id": 1436558,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030571.728, "dur": 0.448, + "args": { + "External id": 1436559,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030573.350, "dur": 0.573, + "args": { + "External id": 1436560,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030574.992, "dur": 0.316, + "args": { + "External id": 1436561,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030577.385, "dur": 0.507, + "args": { + "External id": 1436562,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853030579.159, "dur": 0.483, + "args": { + "External id": 1436563,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853030596.990, "dur": 39.053, + "args": { + "External id": 1436564,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853030707.247, "dur": 454.791, + "args": { + "External id": 1436565,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853030742.368, "dur": 412.919, + "args": { + "External id": 1436566,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16858, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853030753.638, "dur": 393.796, + "args": { + "External id": 1436567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853031191.535, "dur": 3.061, + "args": { + "External id": 1436568,"Record function id": 0, "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": 16860, "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": 2338706, "tid": 2338706, + "ts": 6413853031308.495, "dur": 27317.632, + "args": { + "External id": 1436569,"Record function id": 0, "Ev Idx": 16861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031431.429, "dur": 7.890, + "args": { + "External id": 1436570,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031443.275, "dur": 1.375, + "args": { + "External id": 1436571,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031446.828, "dur": 3.902, + "args": { + "External id": 1436572,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031452.597, "dur": 1.098, + "args": { + "External id": 1436573,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031455.461, "dur": 1.118, + "args": { + "External id": 1436574,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031458.241, "dur": 0.854, + "args": { + "External id": 1436575,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031463.123, "dur": 0.915, + "args": { + "External id": 1436576,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031465.719, "dur": 2.980, + "args": { + "External id": 1436577,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031470.060, "dur": 1.277, + "args": { + "External id": 1436578,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853031472.983, "dur": 0.927, + "args": { + "External id": 1436579,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853031496.987, "dur": 27067.157, + "args": { + "External id": 1436580,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853031515.554, "dur": 27037.884, + "args": { + "External id": 1436581,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853031533.361, "dur": 19.947, + "args": { + "External id": 1436582,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853031557.027, "dur": 26951.381, + "args": { + "External id": 1436583,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853031559.927, "dur": 26946.808, + "args": { + "External id": 1436584,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853031565.381, "dur": 5.691, + "args": { + "External id": 1436585,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853031572.920, "dur": 26929.652, + "args": { + "External id": 1436586,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853058818.003, "dur": 41.415, + "args": { + "External id": 1436587,"Sequence number": 15348896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16879 + } + }, + { + "ph": "s", "id": 439, "pid": 2338706, "tid": 2338706, "ts": 6413853058818.003, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853058839.780, "dur": 12.651, + "args": { + "External id": 1436588,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853058845.256, "dur": 6.888, + "args": { + "External id": 1436589,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853058951.340, "dur": 135.347, + "args": { + "External id": 1436590,"Record function id": 0, "Ev Idx": 16882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853059090.209, "dur": 1361.295, + "args": { + "External id": 1436591,"Record function id": 0, "Ev Idx": 16883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853059146.025, "dur": 1287.807, + "args": { + "External id": 1436592,"Sequence number": 15348897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16884 + } + }, + { + "ph": "s", "id": 438, "pid": 2338706, "tid": 2338706, "ts": 6413853059146.025, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853059238.514, "dur": 60.817, + "args": { + "External id": 1436593,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853059317.802, "dur": 118.790, + "args": { + "External id": 1436594,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853059452.351, "dur": 43.019, + "args": { + "External id": 1436595,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853059504.651, "dur": 34.239, + "args": { + "External id": 1436596,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853059569.292, "dur": 32.599, + "args": { + "External id": 1436597,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853059625.648, "dur": 21.834, + "args": { + "External id": 1436598,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853059674.997, "dur": 157.749, + "args": { + "External id": 1436599,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853059730.232, "dur": 15.327, + "args": { + "External id": 1436600,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853059737.167, "dur": 7.522, + "args": { + "External id": 1436601,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853059749.879, "dur": 4.979, + "args": { + "External id": 1436602,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853059756.316, "dur": 1.340, + "args": { + "External id": 1436603,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853059760.352, "dur": 8.733, + "args": { + "External id": 1436604,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853059847.844, "dur": 57.643, + "args": { + "External id": 1436605,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853059946.907, "dur": 55.110, + "args": { + "External id": 1436606,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853060019.780, "dur": 113.138, + "args": { + "External id": 1436607,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853060148.909, "dur": 45.207, + "args": { + "External id": 1436608,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853060223.272, "dur": 35.136, + "args": { + "External id": 1436609,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853060266.632, "dur": 42.136, + "args": { + "External id": 1436610,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853060329.977, "dur": 23.374, + "args": { + "External id": 1436611,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16903 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 2338706, "tid": 2338706, + "ts": 6413853060526.323, "dur": 95.397, + "args": { + "External id": 1436612,"Record function id": 0, "Ev Idx": 16904 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853060708.859, "dur": 53.132, + "args": { + "External id": 1436613,"Record function id": 0, "Ev Idx": 16905 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338706, "tid": 2338706, + "ts": 6413853060773.333, "dur": 28383.163, + "args": { + "External id": 1436614,"Record function id": 0, "Ev Idx": 16906 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338706, "tid": 2338706, + "ts": 6413853060784.770, "dur": 1185.622, + "args": { + "External id": 1436615,"Record function id": 0, "Ev Idx": 16907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853060883.483, "dur": 11.419, + "args": { + "External id": 1436616,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853060912.537, "dur": 97.641, + "args": { + "External id": 1436617,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060919.305, "dur": 2.595, + "args": { + "External id": 1436618,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060924.993, "dur": 0.725, + "args": { + "External id": 1436619,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060928.125, "dur": 0.536, + "args": { + "External id": 1436620,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060930.412, "dur": 0.499, + "args": { + "External id": 1436621,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060933.115, "dur": 0.591, + "args": { + "External id": 1436622,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060935.941, "dur": 0.400, + "args": { + "External id": 1436623,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060938.213, "dur": 3.198, + "args": { + "External id": 1436624,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060943.350, "dur": 0.683, + "args": { + "External id": 1436625,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853060999.751, "dur": 1.221, + "args": { + "External id": 1436626,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853061026.293, "dur": 114.094, + "args": { + "External id": 1436627,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853061188.885, "dur": 154.101, + "args": { + "External id": 1436628,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853061205.207, "dur": 6.823, + "args": { + "External id": 1436629,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853061219.040, "dur": 14.010, + "args": { + "External id": 1436630,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853061224.381, "dur": 8.172, + "args": { + "External id": 1436631,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 16923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061229.463, "dur": 1.080, + "args": { + "External id": 1436632,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 16924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853061242.527, "dur": 31.327, + "args": { + "External id": 1436633,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061245.586, "dur": 0.804, + "args": { + "External id": 1436634,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061248.492, "dur": 0.634, + "args": { + "External id": 1436635,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061251.309, "dur": 0.940, + "args": { + "External id": 1436636,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061254.405, "dur": 2.892, + "args": { + "External id": 1436637,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061259.321, "dur": 0.456, + "args": { + "External id": 1436638,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061261.795, "dur": 0.439, + "args": { + "External id": 1436639,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061264.013, "dur": 0.459, + "args": { + "External id": 1436640,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061266.184, "dur": 0.569, + "args": { + "External id": 1436641,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853061268.553, "dur": 0.433, + "args": { + "External id": 1436642,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853061290.290, "dur": 43.061, + "args": { + "External id": 1436643,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853061412.587, "dur": 454.409, + "args": { + "External id": 1436644,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 16936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853061438.929, "dur": 422.367, + "args": { + "External id": 1436645,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 16937, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853061450.970, "dur": 402.174, + "args": { + "External id": 1436646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 16938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853061888.277, "dur": 3.322, + "args": { + "External id": 1436647,"Record function id": 0, "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": 16939, "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": 2338706, "tid": 2338706, + "ts": 6413853062021.727, "dur": 26827.960, + "args": { + "External id": 1436648,"Record function id": 0, "Ev Idx": 16940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062188.348, "dur": 7.983, + "args": { + "External id": 1436649,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 16941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062200.438, "dur": 1.695, + "args": { + "External id": 1436650,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062204.169, "dur": 3.978, + "args": { + "External id": 1436651,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062210.032, "dur": 1.421, + "args": { + "External id": 1436652,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062213.187, "dur": 1.112, + "args": { + "External id": 1436653,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 16945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062216.324, "dur": 1.104, + "args": { + "External id": 1436654,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 16946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062219.330, "dur": 1.415, + "args": { + "External id": 1436655,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 16947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062222.333, "dur": 2.506, + "args": { + "External id": 1436656,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062226.504, "dur": 1.279, + "args": { + "External id": 1436657,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853062229.487, "dur": 1.287, + "args": { + "External id": 1436658,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 16950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853062251.975, "dur": 26530.245, + "args": { + "External id": 1436659,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853062271.086, "dur": 26499.892, + "args": { + "External id": 1436660,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 16952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853062292.968, "dur": 20.492, + "args": { + "External id": 1436661,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853062318.088, "dur": 26400.195, + "args": { + "External id": 1436662,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 16954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853062321.375, "dur": 26396.113, + "args": { + "External id": 1436663,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 16955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853062325.970, "dur": 9.077, + "args": { + "External id": 1436664,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853062337.352, "dur": 26374.790, + "args": { + "External id": 1436665,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 16957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853089050.396, "dur": 72.997, + "args": { + "External id": 1436666,"Sequence number": 15348898, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 16958 + } + }, + { + "ph": "s", "id": 437, "pid": 2338706, "tid": 2338706, "ts": 6413853089050.396, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853089102.361, "dur": 14.590, + "args": { + "External id": 1436667,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 16959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853089108.687, "dur": 7.769, + "args": { + "External id": 1436668,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 16960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853089206.289, "dur": 88.841, + "args": { + "External id": 1436669,"Record function id": 0, "Ev Idx": 16961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853089296.455, "dur": 1384.955, + "args": { + "External id": 1436670,"Record function id": 0, "Ev Idx": 16962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853089350.294, "dur": 1313.880, + "args": { + "External id": 1436671,"Sequence number": 15348899, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 16963 + } + }, + { + "ph": "s", "id": 436, "pid": 2338706, "tid": 2338706, "ts": 6413853089350.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853089434.831, "dur": 65.253, + "args": { + "External id": 1436672,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853089552.922, "dur": 118.443, + "args": { + "External id": 1436673,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853089689.657, "dur": 47.848, + "args": { + "External id": 1436674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853089746.839, "dur": 38.254, + "args": { + "External id": 1436675,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 16967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853089812.733, "dur": 34.463, + "args": { + "External id": 1436676,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853089871.682, "dur": 24.381, + "args": { + "External id": 1436677,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 16969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853089922.293, "dur": 225.257, + "args": { + "External id": 1436678,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 16970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853090001.712, "dur": 15.401, + "args": { + "External id": 1436679,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 16971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853090009.014, "dur": 6.995, + "args": { + "External id": 1436680,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853090020.676, "dur": 5.720, + "args": { + "External id": 1436681,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853090028.077, "dur": 1.345, + "args": { + "External id": 1436682,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853090032.831, "dur": 7.724, + "args": { + "External id": 1436683,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853090165.646, "dur": 72.101, + "args": { + "External id": 1436684,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 16976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853090275.712, "dur": 40.677, + "args": { + "External id": 1436685,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 16977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853090329.543, "dur": 53.722, + "args": { + "External id": 1436686,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853090392.140, "dur": 43.007, + "args": { + "External id": 1436687,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 16979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853090458.532, "dur": 31.314, + "args": { + "External id": 1436688,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 16980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853090497.984, "dur": 43.696, + "args": { + "External id": 1436689,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 16981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853090561.032, "dur": 21.017, + "args": { + "External id": 1436690,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 16982 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 2338706, "tid": 2338706, + "ts": 6413853090758.542, "dur": 97.420, + "args": { + "External id": 1436691,"Record function id": 0, "Ev Idx": 16983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853090944.648, "dur": 79.131, + "args": { + "External id": 1436692,"Record function id": 0, "Ev Idx": 16984 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338706, "tid": 2338706, + "ts": 6413853091037.327, "dur": 30532.402, + "args": { + "External id": 1436693,"Record function id": 0, "Ev Idx": 16985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338706, "tid": 2338706, + "ts": 6413853091049.282, "dur": 1109.199, + "args": { + "External id": 1436694,"Record function id": 0, "Ev Idx": 16986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853091191.864, "dur": 12.624, + "args": { + "External id": 1436695,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 16987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853091221.351, "dur": 45.902, + "args": { + "External id": 1436696,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 16988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091228.873, "dur": 2.447, + "args": { + "External id": 1436697,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091234.418, "dur": 0.488, + "args": { + "External id": 1436698,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091236.568, "dur": 0.701, + "args": { + "External id": 1436699,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091238.879, "dur": 0.342, + "args": { + "External id": 1436700,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091240.922, "dur": 0.438, + "args": { + "External id": 1436701,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091248.498, "dur": 0.653, + "args": { + "External id": 1436702,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091251.037, "dur": 3.542, + "args": { + "External id": 1436703,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091256.648, "dur": 0.427, + "args": { + "External id": 1436704,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091258.840, "dur": 0.586, + "args": { + "External id": 1436705,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 16997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853091282.200, "dur": 68.547, + "args": { + "External id": 1436706,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 16998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853091390.926, "dur": 133.985, + "args": { + "External id": 1436707,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 16999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853091404.698, "dur": 4.653, + "args": { + "External id": 1436708,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853091415.840, "dur": 12.397, + "args": { + "External id": 1436709,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853091420.993, "dur": 6.746, + "args": { + "External id": 1436710,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091425.361, "dur": 0.855, + "args": { + "External id": 1436711,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853091435.981, "dur": 28.692, + "args": { + "External id": 1436712,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091438.641, "dur": 0.760, + "args": { + "External id": 1436713,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091441.204, "dur": 0.661, + "args": { + "External id": 1436714,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091443.764, "dur": 0.697, + "args": { + "External id": 1436715,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091446.160, "dur": 3.153, + "args": { + "External id": 1436716,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091451.150, "dur": 0.553, + "args": { + "External id": 1436717,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091453.586, "dur": 0.516, + "args": { + "External id": 1436718,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091455.708, "dur": 0.417, + "args": { + "External id": 1436719,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091457.870, "dur": 0.393, + "args": { + "External id": 1436720,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853091459.723, "dur": 0.521, + "args": { + "External id": 1436721,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853091477.023, "dur": 37.239, + "args": { + "External id": 1436722,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853091589.058, "dur": 415.871, + "args": { + "External id": 1436723,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853091614.879, "dur": 381.651, + "args": { + "External id": 1436724,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17016, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853091627.439, "dur": 342.569, + "args": { + "External id": 1436725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853092030.325, "dur": 3.140, + "args": { + "External id": 1436726,"Record function id": 0, "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": 17018, "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": 2338706, "tid": 2338706, + "ts": 6413853092184.351, "dur": 29109.308, + "args": { + "External id": 1436727,"Record function id": 0, "Ev Idx": 17019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092303.612, "dur": 7.672, + "args": { + "External id": 1436728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092315.487, "dur": 1.222, + "args": { + "External id": 1436729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092318.805, "dur": 4.010, + "args": { + "External id": 1436730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092324.551, "dur": 1.098, + "args": { + "External id": 1436731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092327.456, "dur": 1.101, + "args": { + "External id": 1436732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092330.256, "dur": 1.335, + "args": { + "External id": 1436733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092333.274, "dur": 1.251, + "args": { + "External id": 1436734,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092336.471, "dur": 2.652, + "args": { + "External id": 1436735,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092340.630, "dur": 1.172, + "args": { + "External id": 1436736,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853092343.868, "dur": 0.941, + "args": { + "External id": 1436737,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853092365.579, "dur": 28862.940, + "args": { + "External id": 1436738,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853092383.578, "dur": 28834.056, + "args": { + "External id": 1436739,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853092407.396, "dur": 19.656, + "args": { + "External id": 1436740,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853092431.266, "dur": 28739.219, + "args": { + "External id": 1436741,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853092434.459, "dur": 28735.140, + "args": { + "External id": 1436742,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853092439.170, "dur": 6.024, + "args": { + "External id": 1436743,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853092447.214, "dur": 28717.083, + "args": { + "External id": 1436744,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853121488.862, "dur": 47.621, + "args": { + "External id": 1436745,"Sequence number": 15348900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17037 + } + }, + { + "ph": "s", "id": 435, "pid": 2338706, "tid": 2338706, "ts": 6413853121488.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853121515.864, "dur": 14.690, + "args": { + "External id": 1436746,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853121521.953, "dur": 7.449, + "args": { + "External id": 1436747,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853121623.168, "dur": 89.911, + "args": { + "External id": 1436748,"Record function id": 0, "Ev Idx": 17040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853121714.528, "dur": 1392.827, + "args": { + "External id": 1436749,"Record function id": 0, "Ev Idx": 17041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853121764.066, "dur": 1286.673, + "args": { + "External id": 1436750,"Sequence number": 15348901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17042 + } + }, + { + "ph": "s", "id": 434, "pid": 2338706, "tid": 2338706, "ts": 6413853121764.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853121850.684, "dur": 59.882, + "args": { + "External id": 1436751,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853121929.008, "dur": 177.657, + "args": { + "External id": 1436752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853122132.880, "dur": 54.079, + "args": { + "External id": 1436753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853122195.581, "dur": 35.681, + "args": { + "External id": 1436754,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853122265.792, "dur": 34.118, + "args": { + "External id": 1436755,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853122323.851, "dur": 24.563, + "args": { + "External id": 1436756,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853122374.285, "dur": 161.537, + "args": { + "External id": 1436757,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853122433.376, "dur": 16.349, + "args": { + "External id": 1436758,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853122441.207, "dur": 7.504, + "args": { + "External id": 1436759,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853122454.262, "dur": 4.675, + "args": { + "External id": 1436760,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853122460.464, "dur": 1.540, + "args": { + "External id": 1436761,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853122464.749, "dur": 6.371, + "args": { + "External id": 1436762,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853122549.631, "dur": 58.614, + "args": { + "External id": 1436763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853122642.865, "dur": 35.909, + "args": { + "External id": 1436764,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853122694.464, "dur": 53.458, + "args": { + "External id": 1436765,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853122755.867, "dur": 40.052, + "args": { + "External id": 1436766,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853122822.340, "dur": 30.304, + "args": { + "External id": 1436767,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853122859.477, "dur": 41.724, + "args": { + "External id": 1436768,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853122924.286, "dur": 21.763, + "args": { + "External id": 1436769,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17061 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 2338706, "tid": 2338706, + "ts": 6413853123191.717, "dur": 95.894, + "args": { + "External id": 1436770,"Record function id": 0, "Ev Idx": 17062 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853123375.995, "dur": 52.622, + "args": { + "External id": 1436771,"Record function id": 0, "Ev Idx": 17063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338706, "tid": 2338706, + "ts": 6413853123439.775, "dur": 30768.361, + "args": { + "External id": 1436772,"Record function id": 0, "Ev Idx": 17064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338706, "tid": 2338706, + "ts": 6413853123451.014, "dur": 1153.501, + "args": { + "External id": 1436773,"Record function id": 0, "Ev Idx": 17065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853123553.551, "dur": 11.330, + "args": { + "External id": 1436774,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853123581.885, "dur": 40.328, + "args": { + "External id": 1436775,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123588.727, "dur": 2.405, + "args": { + "External id": 1436776,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123594.144, "dur": 0.536, + "args": { + "External id": 1436777,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123596.643, "dur": 0.590, + "args": { + "External id": 1436778,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123599.210, "dur": 0.511, + "args": { + "External id": 1436779,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123601.867, "dur": 0.550, + "args": { + "External id": 1436780,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123604.703, "dur": 0.709, + "args": { + "External id": 1436781,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123607.655, "dur": 2.861, + "args": { + "External id": 1436782,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123612.663, "dur": 0.404, + "args": { + "External id": 1436783,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123615.013, "dur": 0.461, + "args": { + "External id": 1436784,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853123635.994, "dur": 64.605, + "args": { + "External id": 1436785,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853123777.069, "dur": 149.801, + "args": { + "External id": 1436786,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853123792.709, "dur": 4.696, + "args": { + "External id": 1436787,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853123803.793, "dur": 12.876, + "args": { + "External id": 1436788,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853123809.296, "dur": 6.881, + "args": { + "External id": 1436789,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123813.736, "dur": 1.009, + "args": { + "External id": 1436790,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853123825.505, "dur": 33.325, + "args": { + "External id": 1436791,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123828.667, "dur": 0.558, + "args": { + "External id": 1436792,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123830.984, "dur": 0.501, + "args": { + "External id": 1436793,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123833.356, "dur": 0.757, + "args": { + "External id": 1436794,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123836.136, "dur": 3.093, + "args": { + "External id": 1436795,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123841.971, "dur": 0.719, + "args": { + "External id": 1436796,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123845.094, "dur": 0.666, + "args": { + "External id": 1436797,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123847.725, "dur": 0.431, + "args": { + "External id": 1436798,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123850.592, "dur": 0.444, + "args": { + "External id": 1436799,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853123853.423, "dur": 0.430, + "args": { + "External id": 1436800,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853123873.612, "dur": 43.452, + "args": { + "External id": 1436801,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853124014.451, "dur": 475.390, + "args": { + "External id": 1436802,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853124048.745, "dur": 434.513, + "args": { + "External id": 1436803,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17095, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853124116.292, "dur": 360.817, + "args": { + "External id": 1436804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853124516.153, "dur": 3.116, + "args": { + "External id": 1436805,"Record function id": 0, "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": 17097, "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": 2338706, "tid": 2338706, + "ts": 6413853124629.534, "dur": 29265.127, + "args": { + "External id": 1436806,"Record function id": 0, "Ev Idx": 17098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124749.649, "dur": 7.550, + "args": { + "External id": 1436807,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124760.858, "dur": 1.188, + "args": { + "External id": 1436808,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124764.091, "dur": 3.467, + "args": { + "External id": 1436809,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124769.608, "dur": 0.878, + "args": { + "External id": 1436810,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124771.884, "dur": 1.227, + "args": { + "External id": 1436811,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124774.582, "dur": 0.981, + "args": { + "External id": 1436812,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124777.715, "dur": 0.915, + "args": { + "External id": 1436813,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124780.365, "dur": 2.516, + "args": { + "External id": 1436814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124784.739, "dur": 1.305, + "args": { + "External id": 1436815,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853124787.418, "dur": 0.849, + "args": { + "External id": 1436816,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853124808.129, "dur": 29021.628, + "args": { + "External id": 1436817,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853124826.587, "dur": 28991.321, + "args": { + "External id": 1436818,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853124847.123, "dur": 20.648, + "args": { + "External id": 1436819,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853124872.728, "dur": 28896.888, + "args": { + "External id": 1436820,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853124875.822, "dur": 28892.776, + "args": { + "External id": 1436821,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853124880.410, "dur": 7.662, + "args": { + "External id": 1436822,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853124889.894, "dur": 28873.328, + "args": { + "External id": 1436823,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853154135.862, "dur": 40.539, + "args": { + "External id": 1436824,"Sequence number": 15348902, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17116 + } + }, + { + "ph": "s", "id": 433, "pid": 2338706, "tid": 2338706, "ts": 6413853154135.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853154157.231, "dur": 13.646, + "args": { + "External id": 1436825,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853154162.974, "dur": 7.452, + "args": { + "External id": 1436826,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853154256.873, "dur": 87.965, + "args": { + "External id": 1436827,"Record function id": 0, "Ev Idx": 17119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853154346.300, "dur": 1319.550, + "args": { + "External id": 1436828,"Record function id": 0, "Ev Idx": 17120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853154389.197, "dur": 1261.189, + "args": { + "External id": 1436829,"Sequence number": 15348903, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17121 + } + }, + { + "ph": "s", "id": 432, "pid": 2338706, "tid": 2338706, "ts": 6413853154389.197, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853154473.382, "dur": 63.761, + "args": { + "External id": 1436830,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853154555.217, "dur": 120.724, + "args": { + "External id": 1436831,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853154694.860, "dur": 43.353, + "args": { + "External id": 1436832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853154746.192, "dur": 34.334, + "args": { + "External id": 1436833,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853154810.508, "dur": 32.253, + "args": { + "External id": 1436834,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853154865.465, "dur": 21.126, + "args": { + "External id": 1436835,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853154910.889, "dur": 232.942, + "args": { + "External id": 1436836,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853154973.015, "dur": 38.012, + "args": { + "External id": 1436837,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853154999.961, "dur": 8.629, + "args": { + "External id": 1436838,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853155014.312, "dur": 4.694, + "args": { + "External id": 1436839,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853155020.770, "dur": 1.592, + "args": { + "External id": 1436840,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853155025.783, "dur": 6.100, + "args": { + "External id": 1436841,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853155163.041, "dur": 68.408, + "args": { + "External id": 1436842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853155273.802, "dur": 35.519, + "args": { + "External id": 1436843,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853155320.111, "dur": 49.487, + "args": { + "External id": 1436844,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853155380.826, "dur": 40.007, + "args": { + "External id": 1436845,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853155449.793, "dur": 32.635, + "args": { + "External id": 1436846,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853155489.098, "dur": 40.585, + "args": { + "External id": 1436847,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853155551.356, "dur": 22.847, + "args": { + "External id": 1436848,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17140 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 2338706, "tid": 2338706, + "ts": 6413853155740.079, "dur": 90.032, + "args": { + "External id": 1436849,"Record function id": 0, "Ev Idx": 17141 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853155916.672, "dur": 54.681, + "args": { + "External id": 1436850,"Record function id": 0, "Ev Idx": 17142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338706, "tid": 2338706, + "ts": 6413853156005.263, "dur": 32912.534, + "args": { + "External id": 1436851,"Record function id": 0, "Ev Idx": 17143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338706, "tid": 2338706, + "ts": 6413853156018.288, "dur": 1110.553, + "args": { + "External id": 1436852,"Record function id": 0, "Ev Idx": 17144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853156162.564, "dur": 12.616, + "args": { + "External id": 1436853,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853156193.567, "dur": 44.070, + "args": { + "External id": 1436854,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156200.708, "dur": 2.465, + "args": { + "External id": 1436855,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156206.812, "dur": 0.532, + "args": { + "External id": 1436856,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156209.352, "dur": 0.621, + "args": { + "External id": 1436857,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156212.690, "dur": 0.559, + "args": { + "External id": 1436858,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156215.724, "dur": 0.471, + "args": { + "External id": 1436859,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156218.791, "dur": 0.477, + "args": { + "External id": 1436860,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156221.174, "dur": 3.045, + "args": { + "External id": 1436861,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156226.670, "dur": 0.701, + "args": { + "External id": 1436862,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156229.532, "dur": 0.366, + "args": { + "External id": 1436863,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853156251.246, "dur": 65.300, + "args": { + "External id": 1436864,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853156355.621, "dur": 138.676, + "args": { + "External id": 1436865,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853156369.124, "dur": 4.192, + "args": { + "External id": 1436866,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853156379.610, "dur": 12.296, + "args": { + "External id": 1436867,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853156384.645, "dur": 6.806, + "args": { + "External id": 1436868,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156389.319, "dur": 0.742, + "args": { + "External id": 1436869,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853156399.173, "dur": 31.401, + "args": { + "External id": 1436870,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156402.124, "dur": 0.496, + "args": { + "External id": 1436871,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156404.404, "dur": 0.457, + "args": { + "External id": 1436872,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156407.404, "dur": 0.485, + "args": { + "External id": 1436873,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156409.900, "dur": 2.986, + "args": { + "External id": 1436874,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156414.822, "dur": 0.498, + "args": { + "External id": 1436875,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156417.506, "dur": 0.620, + "args": { + "External id": 1436876,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156420.418, "dur": 0.475, + "args": { + "External id": 1436877,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156422.912, "dur": 0.484, + "args": { + "External id": 1436878,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853156425.133, "dur": 0.607, + "args": { + "External id": 1436879,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853156443.210, "dur": 40.052, + "args": { + "External id": 1436880,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853156559.335, "dur": 396.448, + "args": { + "External id": 1436881,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853156586.777, "dur": 362.939, + "args": { + "External id": 1436882,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17174, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853156599.259, "dur": 344.571, + "args": { + "External id": 1436883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853156999.400, "dur": 4.978, + "args": { + "External id": 1436884,"Record function id": 0, "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": 17176, "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": 2338706, "tid": 2338706, + "ts": 6413853157157.134, "dur": 31493.666, + "args": { + "External id": 1436885,"Record function id": 0, "Ev Idx": 17177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157277.938, "dur": 7.976, + "args": { + "External id": 1436886,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157289.952, "dur": 1.434, + "args": { + "External id": 1436887,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157293.271, "dur": 3.859, + "args": { + "External id": 1436888,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157298.903, "dur": 0.745, + "args": { + "External id": 1436889,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157301.274, "dur": 0.826, + "args": { + "External id": 1436890,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157303.605, "dur": 1.007, + "args": { + "External id": 1436891,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157306.218, "dur": 0.797, + "args": { + "External id": 1436892,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157309.065, "dur": 2.496, + "args": { + "External id": 1436893,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157313.013, "dur": 0.841, + "args": { + "External id": 1436894,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853157316.142, "dur": 0.648, + "args": { + "External id": 1436895,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853157337.944, "dur": 31255.665, + "args": { + "External id": 1436896,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853157356.289, "dur": 31226.428, + "args": { + "External id": 1436897,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853157374.129, "dur": 18.818, + "args": { + "External id": 1436898,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853157396.946, "dur": 31143.096, + "args": { + "External id": 1436899,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853157399.689, "dur": 31138.991, + "args": { + "External id": 1436900,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853157404.405, "dur": 6.196, + "args": { + "External id": 1436901,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853157412.575, "dur": 31121.678, + "args": { + "External id": 1436902,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853188842.441, "dur": 42.628, + "args": { + "External id": 1436903,"Sequence number": 15348904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17195 + } + }, + { + "ph": "s", "id": 431, "pid": 2338706, "tid": 2338706, "ts": 6413853188842.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853188865.094, "dur": 13.287, + "args": { + "External id": 1436904,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853188870.957, "dur": 7.120, + "args": { + "External id": 1436905,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853188967.733, "dur": 134.024, + "args": { + "External id": 1436906,"Record function id": 0, "Ev Idx": 17198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853189105.532, "dur": 1360.330, + "args": { + "External id": 1436907,"Record function id": 0, "Ev Idx": 17199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853189158.206, "dur": 1290.731, + "args": { + "External id": 1436908,"Sequence number": 15348905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17200 + } + }, + { + "ph": "s", "id": 430, "pid": 2338706, "tid": 2338706, "ts": 6413853189158.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853189257.409, "dur": 65.439, + "args": { + "External id": 1436909,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853189342.223, "dur": 119.948, + "args": { + "External id": 1436910,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853189478.518, "dur": 44.616, + "args": { + "External id": 1436911,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853189534.937, "dur": 36.152, + "args": { + "External id": 1436912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853189599.957, "dur": 32.623, + "args": { + "External id": 1436913,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853189655.797, "dur": 21.453, + "args": { + "External id": 1436914,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853189702.876, "dur": 161.875, + "args": { + "External id": 1436915,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853189763.726, "dur": 16.097, + "args": { + "External id": 1436916,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853189771.456, "dur": 7.501, + "args": { + "External id": 1436917,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853189784.278, "dur": 5.014, + "args": { + "External id": 1436918,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853189791.229, "dur": 1.243, + "args": { + "External id": 1436919,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853189795.329, "dur": 6.560, + "args": { + "External id": 1436920,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853189879.238, "dur": 56.970, + "args": { + "External id": 1436921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853189969.414, "dur": 57.693, + "args": { + "External id": 1436922,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853190046.440, "dur": 102.221, + "args": { + "External id": 1436923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853190162.713, "dur": 44.010, + "args": { + "External id": 1436924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853190238.770, "dur": 36.813, + "args": { + "External id": 1436925,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853190282.917, "dur": 44.015, + "args": { + "External id": 1436926,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853190349.873, "dur": 22.640, + "args": { + "External id": 1436927,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 2338706, "tid": 2338706, + "ts": 6413853190542.173, "dur": 92.365, + "args": { + "External id": 1436928,"Record function id": 0, "Ev Idx": 17220 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853190720.725, "dur": 54.244, + "args": { + "External id": 1436929,"Record function id": 0, "Ev Idx": 17221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338706, "tid": 2338706, + "ts": 6413853190786.244, "dur": 32790.234, + "args": { + "External id": 1436930,"Record function id": 0, "Ev Idx": 17222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338706, "tid": 2338706, + "ts": 6413853190796.279, "dur": 1077.270, + "args": { + "External id": 1436931,"Record function id": 0, "Ev Idx": 17223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853190893.857, "dur": 10.823, + "args": { + "External id": 1436932,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853190921.334, "dur": 42.484, + "args": { + "External id": 1436933,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190928.145, "dur": 2.641, + "args": { + "External id": 1436934,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190934.111, "dur": 0.554, + "args": { + "External id": 1436935,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190936.471, "dur": 0.969, + "args": { + "External id": 1436936,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190939.264, "dur": 0.776, + "args": { + "External id": 1436937,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190941.961, "dur": 0.774, + "args": { + "External id": 1436938,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190944.899, "dur": 0.646, + "args": { + "External id": 1436939,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190948.011, "dur": 2.608, + "args": { + "External id": 1436940,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190952.414, "dur": 0.667, + "args": { + "External id": 1436941,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853190954.841, "dur": 1.041, + "args": { + "External id": 1436942,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853190996.334, "dur": 110.755, + "args": { + "External id": 1436943,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853191155.579, "dur": 150.666, + "args": { + "External id": 1436944,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853191171.654, "dur": 6.331, + "args": { + "External id": 1436945,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853191184.527, "dur": 14.247, + "args": { + "External id": 1436946,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853191189.977, "dur": 8.305, + "args": { + "External id": 1436947,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191194.989, "dur": 1.363, + "args": { + "External id": 1436948,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853191208.044, "dur": 30.301, + "args": { + "External id": 1436949,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191210.903, "dur": 0.731, + "args": { + "External id": 1436950,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191213.523, "dur": 0.479, + "args": { + "External id": 1436951,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191216.361, "dur": 0.492, + "args": { + "External id": 1436952,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191219.087, "dur": 2.898, + "args": { + "External id": 1436953,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191223.617, "dur": 0.364, + "args": { + "External id": 1436954,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191225.960, "dur": 0.476, + "args": { + "External id": 1436955,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191228.449, "dur": 0.462, + "args": { + "External id": 1436956,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191230.696, "dur": 0.491, + "args": { + "External id": 1436957,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853191232.772, "dur": 0.684, + "args": { + "External id": 1436958,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853191255.850, "dur": 40.586, + "args": { + "External id": 1436959,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853191374.324, "dur": 396.034, + "args": { + "External id": 1436960,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853191403.863, "dur": 361.097, + "args": { + "External id": 1436961,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17253, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853191415.805, "dur": 342.923, + "args": { + "External id": 1436962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853191794.501, "dur": 2.459, + "args": { + "External id": 1436963,"Record function id": 0, "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": 17255, "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": 2338706, "tid": 2338706, + "ts": 6413853191898.788, "dur": 31415.107, + "args": { + "External id": 1436964,"Record function id": 0, "Ev Idx": 17256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192038.436, "dur": 7.864, + "args": { + "External id": 1436965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192050.616, "dur": 1.142, + "args": { + "External id": 1436966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192053.849, "dur": 45.881, + "args": { + "External id": 1436967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192106.641, "dur": 1.631, + "args": { + "External id": 1436968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192111.030, "dur": 1.301, + "args": { + "External id": 1436969,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192114.830, "dur": 1.750, + "args": { + "External id": 1436970,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192119.721, "dur": 1.365, + "args": { + "External id": 1436971,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192124.736, "dur": 2.974, + "args": { + "External id": 1436972,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192130.445, "dur": 1.356, + "args": { + "External id": 1436973,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853192134.811, "dur": 1.293, + "args": { + "External id": 1436974,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853192164.653, "dur": 31082.036, + "args": { + "External id": 1436975,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853192189.945, "dur": 31045.709, + "args": { + "External id": 1436976,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853192210.931, "dur": 20.114, + "args": { + "External id": 1436977,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853192235.118, "dur": 30954.239, + "args": { + "External id": 1436978,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853192239.211, "dur": 30949.026, + "args": { + "External id": 1436979,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853192243.894, "dur": 7.607, + "args": { + "External id": 1436980,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853192253.241, "dur": 30930.487, + "args": { + "External id": 1436981,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853223506.226, "dur": 39.832, + "args": { + "External id": 1436982,"Sequence number": 15348906, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17274 + } + }, + { + "ph": "s", "id": 429, "pid": 2338706, "tid": 2338706, "ts": 6413853223506.226, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853223527.287, "dur": 13.270, + "args": { + "External id": 1436983,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853223533.206, "dur": 7.087, + "args": { + "External id": 1436984,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853223624.876, "dur": 85.462, + "args": { + "External id": 1436985,"Record function id": 0, "Ev Idx": 17277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853223712.178, "dur": 1376.095, + "args": { + "External id": 1436986,"Record function id": 0, "Ev Idx": 17278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853223755.949, "dur": 1281.159, + "args": { + "External id": 1436987,"Sequence number": 15348907, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17279 + } + }, + { + "ph": "s", "id": 428, "pid": 2338706, "tid": 2338706, "ts": 6413853223755.949, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853223839.437, "dur": 58.990, + "args": { + "External id": 1436988,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853223915.657, "dur": 134.223, + "args": { + "External id": 1436989,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853224110.843, "dur": 55.679, + "args": { + "External id": 1436990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853224179.872, "dur": 39.691, + "args": { + "External id": 1436991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853224254.834, "dur": 36.685, + "args": { + "External id": 1436992,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853224315.251, "dur": 22.514, + "args": { + "External id": 1436993,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853224368.533, "dur": 157.780, + "args": { + "External id": 1436994,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853224426.215, "dur": 14.570, + "args": { + "External id": 1436995,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853224433.639, "dur": 6.045, + "args": { + "External id": 1436996,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853224444.171, "dur": 5.396, + "args": { + "External id": 1436997,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853224451.210, "dur": 1.422, + "args": { + "External id": 1436998,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853224455.552, "dur": 6.614, + "args": { + "External id": 1436999,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853224543.338, "dur": 61.269, + "args": { + "External id": 1437000,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853224640.983, "dur": 35.696, + "args": { + "External id": 1437001,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853224691.582, "dur": 51.155, + "args": { + "External id": 1437002,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853224752.146, "dur": 43.175, + "args": { + "External id": 1437003,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853224818.974, "dur": 32.071, + "args": { + "External id": 1437004,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853224859.263, "dur": 43.181, + "args": { + "External id": 1437005,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853224921.370, "dur": 22.557, + "args": { + "External id": 1437006,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 2338706, "tid": 2338706, + "ts": 6413853225169.248, "dur": 91.905, + "args": { + "External id": 1437007,"Record function id": 0, "Ev Idx": 17299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853225349.670, "dur": 53.605, + "args": { + "External id": 1437008,"Record function id": 0, "Ev Idx": 17300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338706, "tid": 2338706, + "ts": 6413853225415.308, "dur": 33804.895, + "args": { + "External id": 1437009,"Record function id": 0, "Ev Idx": 17301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338706, "tid": 2338706, + "ts": 6413853225425.351, "dur": 1108.753, + "args": { + "External id": 1437010,"Record function id": 0, "Ev Idx": 17302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853225524.882, "dur": 11.440, + "args": { + "External id": 1437011,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853225551.637, "dur": 39.611, + "args": { + "External id": 1437012,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225558.294, "dur": 2.612, + "args": { + "External id": 1437013,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225564.151, "dur": 0.467, + "args": { + "External id": 1437014,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225566.437, "dur": 0.526, + "args": { + "External id": 1437015,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225568.917, "dur": 0.733, + "args": { + "External id": 1437016,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225571.266, "dur": 0.755, + "args": { + "External id": 1437017,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225574.090, "dur": 0.646, + "args": { + "External id": 1437018,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225576.051, "dur": 3.553, + "args": { + "External id": 1437019,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225581.325, "dur": 0.760, + "args": { + "External id": 1437020,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225583.584, "dur": 0.767, + "args": { + "External id": 1437021,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853225605.719, "dur": 62.359, + "args": { + "External id": 1437022,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853225705.319, "dur": 134.146, + "args": { + "External id": 1437023,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853225718.693, "dur": 4.010, + "args": { + "External id": 1437024,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853225728.779, "dur": 12.575, + "args": { + "External id": 1437025,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853225734.107, "dur": 6.813, + "args": { + "External id": 1437026,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225738.692, "dur": 0.788, + "args": { + "External id": 1437027,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853225749.295, "dur": 34.622, + "args": { + "External id": 1437028,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225751.819, "dur": 0.743, + "args": { + "External id": 1437029,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225754.448, "dur": 0.889, + "args": { + "External id": 1437030,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225756.831, "dur": 0.602, + "args": { + "External id": 1437031,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225759.451, "dur": 8.446, + "args": { + "External id": 1437032,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225769.520, "dur": 0.446, + "args": { + "External id": 1437033,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225771.836, "dur": 0.616, + "args": { + "External id": 1437034,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225773.767, "dur": 0.682, + "args": { + "External id": 1437035,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225776.628, "dur": 0.715, + "args": { + "External id": 1437036,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853225778.887, "dur": 0.697, + "args": { + "External id": 1437037,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853225795.899, "dur": 34.213, + "args": { + "External id": 1437038,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853225899.729, "dur": 514.710, + "args": { + "External id": 1437039,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853225926.269, "dur": 481.293, + "args": { + "External id": 1437040,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17332, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853225938.112, "dur": 462.091, + "args": { + "External id": 1437041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853226443.890, "dur": 3.280, + "args": { + "External id": 1437042,"Record function id": 0, "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": 17334, "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": 2338706, "tid": 2338706, + "ts": 6413853226559.552, "dur": 32323.301, + "args": { + "External id": 1437043,"Record function id": 0, "Ev Idx": 17335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226680.093, "dur": 7.735, + "args": { + "External id": 1437044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226691.911, "dur": 1.374, + "args": { + "External id": 1437045,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226695.380, "dur": 3.135, + "args": { + "External id": 1437046,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226700.449, "dur": 0.834, + "args": { + "External id": 1437047,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226702.829, "dur": 1.104, + "args": { + "External id": 1437048,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226705.251, "dur": 1.175, + "args": { + "External id": 1437049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226708.473, "dur": 1.221, + "args": { + "External id": 1437050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226711.671, "dur": 2.358, + "args": { + "External id": 1437051,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226715.408, "dur": 0.704, + "args": { + "External id": 1437052,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853226718.017, "dur": 0.917, + "args": { + "External id": 1437053,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853226740.058, "dur": 32077.205, + "args": { + "External id": 1437054,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853226758.657, "dur": 32046.645, + "args": { + "External id": 1437055,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853226777.881, "dur": 21.979, + "args": { + "External id": 1437056,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853226805.081, "dur": 31952.317, + "args": { + "External id": 1437057,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853226808.178, "dur": 31948.345, + "args": { + "External id": 1437058,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853226835.110, "dur": 16.930, + "args": { + "External id": 1437059,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853226854.236, "dur": 31896.915, + "args": { + "External id": 1437060,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853259130.274, "dur": 51.096, + "args": { + "External id": 1437061,"Sequence number": 15348908, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17353 + } + }, + { + "ph": "s", "id": 427, "pid": 2338706, "tid": 2338706, "ts": 6413853259130.274, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853259159.225, "dur": 15.374, + "args": { + "External id": 1437062,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853259165.204, "dur": 8.966, + "args": { + "External id": 1437063,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853259276.282, "dur": 87.081, + "args": { + "External id": 1437064,"Record function id": 0, "Ev Idx": 17356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853259365.104, "dur": 1364.740, + "args": { + "External id": 1437065,"Record function id": 0, "Ev Idx": 17357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853259415.232, "dur": 1296.366, + "args": { + "External id": 1437066,"Sequence number": 15348909, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17358 + } + }, + { + "ph": "s", "id": 426, "pid": 2338706, "tid": 2338706, "ts": 6413853259415.232, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853259500.957, "dur": 65.470, + "args": { + "External id": 1437067,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853259586.668, "dur": 120.025, + "args": { + "External id": 1437068,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853259722.437, "dur": 42.774, + "args": { + "External id": 1437069,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853259776.493, "dur": 36.240, + "args": { + "External id": 1437070,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853259842.160, "dur": 30.251, + "args": { + "External id": 1437071,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853259896.906, "dur": 21.248, + "args": { + "External id": 1437072,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853259942.253, "dur": 225.174, + "args": { + "External id": 1437073,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853260021.032, "dur": 16.051, + "args": { + "External id": 1437074,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853260028.016, "dur": 7.858, + "args": { + "External id": 1437075,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853260041.505, "dur": 5.324, + "args": { + "External id": 1437076,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853260048.152, "dur": 1.210, + "args": { + "External id": 1437077,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853260089.376, "dur": 8.697, + "args": { + "External id": 1437078,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853260185.507, "dur": 70.461, + "args": { + "External id": 1437079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853260297.271, "dur": 39.181, + "args": { + "External id": 1437080,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853260352.550, "dur": 58.270, + "args": { + "External id": 1437081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853260420.088, "dur": 45.073, + "args": { + "External id": 1437082,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853260490.460, "dur": 36.165, + "args": { + "External id": 1437083,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853260534.890, "dur": 48.415, + "args": { + "External id": 1437084,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853260605.536, "dur": 23.954, + "args": { + "External id": 1437085,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17377 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 2338706, "tid": 2338706, + "ts": 6413853260802.977, "dur": 95.550, + "args": { + "External id": 1437086,"Record function id": 0, "Ev Idx": 17378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853261010.922, "dur": 100.523, + "args": { + "External id": 1437087,"Record function id": 0, "Ev Idx": 17379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338706, "tid": 2338706, + "ts": 6413853261125.379, "dur": 33671.527, + "args": { + "External id": 1437088,"Record function id": 0, "Ev Idx": 17380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338706, "tid": 2338706, + "ts": 6413853261136.459, "dur": 1080.964, + "args": { + "External id": 1437089,"Record function id": 0, "Ev Idx": 17381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853261240.153, "dur": 11.768, + "args": { + "External id": 1437090,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853261269.501, "dur": 45.312, + "args": { + "External id": 1437091,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261276.543, "dur": 2.767, + "args": { + "External id": 1437092,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261282.388, "dur": 0.694, + "args": { + "External id": 1437093,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261287.995, "dur": 0.639, + "args": { + "External id": 1437094,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261291.050, "dur": 0.893, + "args": { + "External id": 1437095,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261293.607, "dur": 0.528, + "args": { + "External id": 1437096,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261296.702, "dur": 0.761, + "args": { + "External id": 1437097,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261299.034, "dur": 3.526, + "args": { + "External id": 1437098,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261304.729, "dur": 0.539, + "args": { + "External id": 1437099,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261306.880, "dur": 0.850, + "args": { + "External id": 1437100,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853261327.622, "dur": 70.225, + "args": { + "External id": 1437101,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853261437.208, "dur": 135.707, + "args": { + "External id": 1437102,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853261451.917, "dur": 4.120, + "args": { + "External id": 1437103,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853261462.175, "dur": 12.724, + "args": { + "External id": 1437104,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853261467.606, "dur": 6.749, + "args": { + "External id": 1437105,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261472.186, "dur": 0.824, + "args": { + "External id": 1437106,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853261482.243, "dur": 27.045, + "args": { + "External id": 1437107,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261484.590, "dur": 0.810, + "args": { + "External id": 1437108,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261487.155, "dur": 0.767, + "args": { + "External id": 1437109,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261489.374, "dur": 0.550, + "args": { + "External id": 1437110,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261492.122, "dur": 2.683, + "args": { + "External id": 1437111,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261496.325, "dur": 0.365, + "args": { + "External id": 1437112,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261498.449, "dur": 0.505, + "args": { + "External id": 1437113,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261500.507, "dur": 0.466, + "args": { + "External id": 1437114,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261502.600, "dur": 0.522, + "args": { + "External id": 1437115,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853261504.338, "dur": 0.472, + "args": { + "External id": 1437116,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853261522.860, "dur": 41.103, + "args": { + "External id": 1437117,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853261635.050, "dur": 463.193, + "args": { + "External id": 1437118,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853261663.707, "dur": 391.535, + "args": { + "External id": 1437119,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17411, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853261675.864, "dur": 372.121, + "args": { + "External id": 1437120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853262127.058, "dur": 3.726, + "args": { + "External id": 1437121,"Record function id": 0, "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": 17413, "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": 2338706, "tid": 2338706, + "ts": 6413853262241.900, "dur": 32318.423, + "args": { + "External id": 1437122,"Record function id": 0, "Ev Idx": 17414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262361.474, "dur": 7.797, + "args": { + "External id": 1437123,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262373.517, "dur": 1.069, + "args": { + "External id": 1437124,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262376.569, "dur": 3.173, + "args": { + "External id": 1437125,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262381.681, "dur": 1.546, + "args": { + "External id": 1437126,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262384.744, "dur": 1.109, + "args": { + "External id": 1437127,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262387.324, "dur": 0.954, + "args": { + "External id": 1437128,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262390.044, "dur": 1.109, + "args": { + "External id": 1437129,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262394.001, "dur": 1.896, + "args": { + "External id": 1437130,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262397.429, "dur": 1.114, + "args": { + "External id": 1437131,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853262400.203, "dur": 0.775, + "args": { + "External id": 1437132,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853262421.104, "dur": 32080.937, + "args": { + "External id": 1437133,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853262439.538, "dur": 32051.627, + "args": { + "External id": 1437134,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853262457.755, "dur": 19.178, + "args": { + "External id": 1437135,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853262481.329, "dur": 31963.805, + "args": { + "External id": 1437136,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853262484.161, "dur": 31959.654, + "args": { + "External id": 1437137,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853262488.478, "dur": 6.669, + "args": { + "External id": 1437138,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853262496.838, "dur": 31942.506, + "args": { + "External id": 1437139,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853294729.174, "dur": 38.879, + "args": { + "External id": 1437140,"Sequence number": 15348910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17432 + } + }, + { + "ph": "s", "id": 425, "pid": 2338706, "tid": 2338706, "ts": 6413853294729.174, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853294749.485, "dur": 12.992, + "args": { + "External id": 1437141,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853294755.160, "dur": 7.051, + "args": { + "External id": 1437142,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853294843.824, "dur": 83.144, + "args": { + "External id": 1437143,"Record function id": 0, "Ev Idx": 17435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853294928.506, "dur": 1361.030, + "args": { + "External id": 1437144,"Record function id": 0, "Ev Idx": 17436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853294969.978, "dur": 1303.328, + "args": { + "External id": 1437145,"Sequence number": 15348911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17437 + } + }, + { + "ph": "s", "id": 424, "pid": 2338706, "tid": 2338706, "ts": 6413853294969.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853295102.668, "dur": 61.219, + "args": { + "External id": 1437146,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853295182.862, "dur": 115.551, + "args": { + "External id": 1437147,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853295314.145, "dur": 45.313, + "args": { + "External id": 1437148,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853295370.766, "dur": 37.421, + "args": { + "External id": 1437149,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853295442.010, "dur": 31.616, + "args": { + "External id": 1437150,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853295497.771, "dur": 23.201, + "args": { + "External id": 1437151,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853295546.233, "dur": 155.526, + "args": { + "External id": 1437152,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853295605.384, "dur": 15.307, + "args": { + "External id": 1437153,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853295612.591, "dur": 7.108, + "args": { + "External id": 1437154,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853295625.258, "dur": 4.702, + "args": { + "External id": 1437155,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853295631.479, "dur": 1.336, + "args": { + "External id": 1437156,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853295635.993, "dur": 6.279, + "args": { + "External id": 1437157,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853295715.360, "dur": 56.941, + "args": { + "External id": 1437158,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853295804.555, "dur": 39.782, + "args": { + "External id": 1437159,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853295855.735, "dur": 49.267, + "args": { + "External id": 1437160,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853295915.826, "dur": 42.763, + "args": { + "External id": 1437161,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853296002.413, "dur": 35.884, + "args": { + "External id": 1437162,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853296089.247, "dur": 56.459, + "args": { + "External id": 1437163,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853296173.384, "dur": 23.974, + "args": { + "External id": 1437164,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17456 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 2338706, "tid": 2338706, + "ts": 6413853296365.125, "dur": 91.913, + "args": { + "External id": 1437165,"Record function id": 0, "Ev Idx": 17457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853296543.117, "dur": 55.500, + "args": { + "External id": 1437166,"Record function id": 0, "Ev Idx": 17458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338706, "tid": 2338706, + "ts": 6413853296609.281, "dur": 31344.723, + "args": { + "External id": 1437167,"Record function id": 0, "Ev Idx": 17459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338706, "tid": 2338706, + "ts": 6413853296619.956, "dur": 1185.923, + "args": { + "External id": 1437168,"Record function id": 0, "Ev Idx": 17460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853296719.431, "dur": 9.677, + "args": { + "External id": 1437169,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853296744.756, "dur": 38.003, + "args": { + "External id": 1437170,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296751.498, "dur": 2.498, + "args": { + "External id": 1437171,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296756.631, "dur": 0.926, + "args": { + "External id": 1437172,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296759.630, "dur": 0.726, + "args": { + "External id": 1437173,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296762.555, "dur": 0.561, + "args": { + "External id": 1437174,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296764.862, "dur": 0.534, + "args": { + "External id": 1437175,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296767.072, "dur": 0.475, + "args": { + "External id": 1437176,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296769.249, "dur": 2.803, + "args": { + "External id": 1437177,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296773.636, "dur": 0.414, + "args": { + "External id": 1437178,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296775.848, "dur": 0.541, + "args": { + "External id": 1437179,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853296795.556, "dur": 61.127, + "args": { + "External id": 1437180,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853296893.317, "dur": 303.575, + "args": { + "External id": 1437181,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853296905.999, "dur": 4.024, + "args": { + "External id": 1437182,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853296916.147, "dur": 83.653, + "args": { + "External id": 1437183,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853296920.956, "dur": 78.257, + "args": { + "External id": 1437184,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853296975.108, "dur": 20.407, + "args": { + "External id": 1437185,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853297011.453, "dur": 28.793, + "args": { + "External id": 1437186,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297014.345, "dur": 0.743, + "args": { + "External id": 1437187,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297017.346, "dur": 0.666, + "args": { + "External id": 1437188,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297019.632, "dur": 0.453, + "args": { + "External id": 1437189,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297022.217, "dur": 3.444, + "args": { + "External id": 1437190,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297027.096, "dur": 0.472, + "args": { + "External id": 1437191,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297029.095, "dur": 0.633, + "args": { + "External id": 1437192,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297031.123, "dur": 0.485, + "args": { + "External id": 1437193,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297033.772, "dur": 0.502, + "args": { + "External id": 1437194,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853297035.697, "dur": 0.487, + "args": { + "External id": 1437195,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853297115.627, "dur": 62.765, + "args": { + "External id": 1437196,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853297277.622, "dur": 424.532, + "args": { + "External id": 1437197,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853297311.030, "dur": 385.198, + "args": { + "External id": 1437198,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17490, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853297326.123, "dur": 364.028, + "args": { + "External id": 1437199,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853297724.925, "dur": 2.756, + "args": { + "External id": 1437200,"Record function id": 0, "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": 17492, "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": 2338706, "tid": 2338706, + "ts": 6413853297829.692, "dur": 29885.120, + "args": { + "External id": 1437201,"Record function id": 0, "Ev Idx": 17493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853297949.860, "dur": 7.732, + "args": { + "External id": 1437202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853297961.432, "dur": 1.140, + "args": { + "External id": 1437203,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853297964.515, "dur": 7.332, + "args": { + "External id": 1437204,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853297973.992, "dur": 1.062, + "args": { + "External id": 1437205,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853297998.080, "dur": 1.696, + "args": { + "External id": 1437206,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853298004.389, "dur": 1.038, + "args": { + "External id": 1437207,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853298007.644, "dur": 1.003, + "args": { + "External id": 1437208,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853298010.658, "dur": 2.426, + "args": { + "External id": 1437209,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853298015.004, "dur": 0.808, + "args": { + "External id": 1437210,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853298017.388, "dur": 0.775, + "args": { + "External id": 1437211,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853298038.838, "dur": 29615.089, + "args": { + "External id": 1437212,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853298094.761, "dur": 29548.378, + "args": { + "External id": 1437213,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853298114.963, "dur": 20.035, + "args": { + "External id": 1437214,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853298139.315, "dur": 29460.401, + "args": { + "External id": 1437215,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853298142.406, "dur": 29455.389, + "args": { + "External id": 1437216,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853298147.134, "dur": 6.800, + "args": { + "External id": 1437217,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853298155.742, "dur": 29438.229, + "args": { + "External id": 1437218,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853327887.867, "dur": 36.233, + "args": { + "External id": 1437219,"Sequence number": 15348912, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17511 + } + }, + { + "ph": "s", "id": 423, "pid": 2338706, "tid": 2338706, "ts": 6413853327887.867, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853327908.054, "dur": 10.560, + "args": { + "External id": 1437220,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853327912.636, "dur": 5.708, + "args": { + "External id": 1437221,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853328015.647, "dur": 121.558, + "args": { + "External id": 1437222,"Record function id": 0, "Ev Idx": 17514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853328141.125, "dur": 1306.450, + "args": { + "External id": 1437223,"Record function id": 0, "Ev Idx": 17515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853328186.889, "dur": 1243.545, + "args": { + "External id": 1437224,"Sequence number": 15348913, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17516 + } + }, + { + "ph": "s", "id": 422, "pid": 2338706, "tid": 2338706, "ts": 6413853328186.889, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853328273.643, "dur": 59.348, + "args": { + "External id": 1437225,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853328347.445, "dur": 119.763, + "args": { + "External id": 1437226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853328483.094, "dur": 42.090, + "args": { + "External id": 1437227,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853328535.906, "dur": 33.827, + "args": { + "External id": 1437228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853328602.400, "dur": 30.383, + "args": { + "External id": 1437229,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853328656.424, "dur": 22.176, + "args": { + "External id": 1437230,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853328705.028, "dur": 162.764, + "args": { + "External id": 1437231,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853328764.542, "dur": 14.749, + "args": { + "External id": 1437232,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853328771.815, "dur": 6.406, + "args": { + "External id": 1437233,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853328782.569, "dur": 4.951, + "args": { + "External id": 1437234,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853328789.122, "dur": 1.461, + "args": { + "External id": 1437235,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853328793.407, "dur": 10.117, + "args": { + "External id": 1437236,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853328880.625, "dur": 52.690, + "args": { + "External id": 1437237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853328964.463, "dur": 52.200, + "args": { + "External id": 1437238,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853329034.665, "dur": 97.311, + "args": { + "External id": 1437239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853329146.065, "dur": 46.824, + "args": { + "External id": 1437240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853329217.779, "dur": 36.447, + "args": { + "External id": 1437241,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853329262.626, "dur": 43.257, + "args": { + "External id": 1437242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853329326.074, "dur": 23.319, + "args": { + "External id": 1437243,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 2338706, "tid": 2338706, + "ts": 6413853329521.912, "dur": 92.728, + "args": { + "External id": 1437244,"Record function id": 0, "Ev Idx": 17536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853329701.135, "dur": 54.820, + "args": { + "External id": 1437245,"Record function id": 0, "Ev Idx": 17537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338706, "tid": 2338706, + "ts": 6413853329766.964, "dur": 29779.565, + "args": { + "External id": 1437246,"Record function id": 0, "Ev Idx": 17538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338706, "tid": 2338706, + "ts": 6413853329778.497, "dur": 1065.914, + "args": { + "External id": 1437247,"Record function id": 0, "Ev Idx": 17539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853329878.083, "dur": 9.369, + "args": { + "External id": 1437248,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853329902.705, "dur": 39.733, + "args": { + "External id": 1437249,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329909.451, "dur": 2.424, + "args": { + "External id": 1437250,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329914.678, "dur": 0.535, + "args": { + "External id": 1437251,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329917.811, "dur": 0.493, + "args": { + "External id": 1437252,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329919.862, "dur": 0.521, + "args": { + "External id": 1437253,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329922.493, "dur": 0.577, + "args": { + "External id": 1437254,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329924.977, "dur": 0.957, + "args": { + "External id": 1437255,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329927.910, "dur": 3.005, + "args": { + "External id": 1437256,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329932.750, "dur": 0.615, + "args": { + "External id": 1437257,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853329935.312, "dur": 0.447, + "args": { + "External id": 1437258,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853329956.857, "dur": 77.542, + "args": { + "External id": 1437259,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853330122.993, "dur": 145.149, + "args": { + "External id": 1437260,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853330138.435, "dur": 6.578, + "args": { + "External id": 1437261,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853330151.673, "dur": 14.433, + "args": { + "External id": 1437262,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853330157.400, "dur": 8.176, + "args": { + "External id": 1437263,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330162.320, "dur": 1.080, + "args": { + "External id": 1437264,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853330174.388, "dur": 29.206, + "args": { + "External id": 1437265,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330177.354, "dur": 0.605, + "args": { + "External id": 1437266,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330180.393, "dur": 0.572, + "args": { + "External id": 1437267,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330182.445, "dur": 0.845, + "args": { + "External id": 1437268,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330185.226, "dur": 2.799, + "args": { + "External id": 1437269,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330189.770, "dur": 0.654, + "args": { + "External id": 1437270,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330192.200, "dur": 0.637, + "args": { + "External id": 1437271,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330194.483, "dur": 0.416, + "args": { + "External id": 1437272,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330196.673, "dur": 0.412, + "args": { + "External id": 1437273,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853330198.733, "dur": 0.496, + "args": { + "External id": 1437274,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853330218.646, "dur": 39.355, + "args": { + "External id": 1437275,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853330335.633, "dur": 402.426, + "args": { + "External id": 1437276,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853330365.953, "dur": 366.710, + "args": { + "External id": 1437277,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17569, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853330378.336, "dur": 344.509, + "args": { + "External id": 1437278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853330763.585, "dur": 2.811, + "args": { + "External id": 1437279,"Record function id": 0, "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": 17571, "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": 2338706, "tid": 2338706, + "ts": 6413853330869.311, "dur": 28399.225, + "args": { + "External id": 1437280,"Record function id": 0, "Ev Idx": 17572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331007.856, "dur": 8.788, + "args": { + "External id": 1437281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331021.738, "dur": 1.036, + "args": { + "External id": 1437282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331024.821, "dur": 4.001, + "args": { + "External id": 1437283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331030.677, "dur": 0.986, + "args": { + "External id": 1437284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331033.288, "dur": 0.890, + "args": { + "External id": 1437285,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331035.769, "dur": 0.842, + "args": { + "External id": 1437286,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331038.365, "dur": 0.774, + "args": { + "External id": 1437287,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331040.983, "dur": 2.099, + "args": { + "External id": 1437288,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331044.795, "dur": 0.962, + "args": { + "External id": 1437289,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853331047.449, "dur": 0.760, + "args": { + "External id": 1437290,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853331108.508, "dur": 28097.936, + "args": { + "External id": 1437291,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853331129.858, "dur": 28066.089, + "args": { + "External id": 1437292,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853331150.456, "dur": 20.467, + "args": { + "External id": 1437293,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853331177.583, "dur": 27971.419, + "args": { + "External id": 1437294,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853331180.596, "dur": 27967.689, + "args": { + "External id": 1437295,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853331185.323, "dur": 7.066, + "args": { + "External id": 1437296,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853331194.459, "dur": 27948.908, + "args": { + "External id": 1437297,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853359469.362, "dur": 44.251, + "args": { + "External id": 1437298,"Sequence number": 15348914, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17590 + } + }, + { + "ph": "s", "id": 421, "pid": 2338706, "tid": 2338706, "ts": 6413853359469.362, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853359494.181, "dur": 12.488, + "args": { + "External id": 1437299,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853359499.443, "dur": 6.912, + "args": { + "External id": 1437300,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853359599.369, "dur": 84.547, + "args": { + "External id": 1437301,"Record function id": 0, "Ev Idx": 17593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853359685.710, "dur": 1444.886, + "args": { + "External id": 1437302,"Record function id": 0, "Ev Idx": 17594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853359735.221, "dur": 1374.379, + "args": { + "External id": 1437303,"Sequence number": 15348915, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17595 + } + }, + { + "ph": "s", "id": 420, "pid": 2338706, "tid": 2338706, "ts": 6413853359735.221, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853359816.278, "dur": 57.654, + "args": { + "External id": 1437304,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853359887.895, "dur": 130.304, + "args": { + "External id": 1437305,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853360038.926, "dur": 109.368, + "args": { + "External id": 1437306,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853360172.038, "dur": 52.523, + "args": { + "External id": 1437307,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853360267.635, "dur": 37.881, + "args": { + "External id": 1437308,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853360330.529, "dur": 23.082, + "args": { + "External id": 1437309,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853360383.031, "dur": 162.955, + "args": { + "External id": 1437310,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853360442.610, "dur": 16.095, + "args": { + "External id": 1437311,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853360450.217, "dur": 7.458, + "args": { + "External id": 1437312,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853360463.333, "dur": 5.161, + "args": { + "External id": 1437313,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853360470.205, "dur": 1.425, + "args": { + "External id": 1437314,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853360474.728, "dur": 7.153, + "args": { + "External id": 1437315,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853360561.142, "dur": 61.919, + "args": { + "External id": 1437316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853360658.700, "dur": 36.792, + "args": { + "External id": 1437317,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853360707.307, "dur": 51.806, + "args": { + "External id": 1437318,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853360770.503, "dur": 41.663, + "args": { + "External id": 1437319,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853360836.511, "dur": 31.900, + "args": { + "External id": 1437320,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853360876.280, "dur": 42.021, + "args": { + "External id": 1437321,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853360938.686, "dur": 20.686, + "args": { + "External id": 1437322,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17614 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 2338706, "tid": 2338706, + "ts": 6413853361209.042, "dur": 95.029, + "args": { + "External id": 1437323,"Record function id": 0, "Ev Idx": 17615 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853361394.632, "dur": 55.671, + "args": { + "External id": 1437324,"Record function id": 0, "Ev Idx": 17616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338706, "tid": 2338706, + "ts": 6413853361460.815, "dur": 30168.058, + "args": { + "External id": 1437325,"Record function id": 0, "Ev Idx": 17617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338706, "tid": 2338706, + "ts": 6413853361470.672, "dur": 1079.750, + "args": { + "External id": 1437326,"Record function id": 0, "Ev Idx": 17618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853361569.990, "dur": 11.666, + "args": { + "External id": 1437327,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853361598.899, "dur": 42.269, + "args": { + "External id": 1437328,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361606.211, "dur": 2.441, + "args": { + "External id": 1437329,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361611.457, "dur": 0.728, + "args": { + "External id": 1437330,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361617.014, "dur": 0.414, + "args": { + "External id": 1437331,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361619.261, "dur": 0.481, + "args": { + "External id": 1437332,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361621.572, "dur": 0.923, + "args": { + "External id": 1437333,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361624.045, "dur": 0.609, + "args": { + "External id": 1437334,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361626.273, "dur": 3.042, + "args": { + "External id": 1437335,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361631.107, "dur": 0.745, + "args": { + "External id": 1437336,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361633.787, "dur": 0.434, + "args": { + "External id": 1437337,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853361653.923, "dur": 64.541, + "args": { + "External id": 1437338,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853361757.619, "dur": 129.953, + "args": { + "External id": 1437339,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853361770.938, "dur": 4.652, + "args": { + "External id": 1437340,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853361781.537, "dur": 11.952, + "args": { + "External id": 1437341,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853361786.758, "dur": 6.257, + "args": { + "External id": 1437342,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361791.042, "dur": 0.558, + "args": { + "External id": 1437343,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853361801.047, "dur": 27.947, + "args": { + "External id": 1437344,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361803.798, "dur": 0.695, + "args": { + "External id": 1437345,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361806.163, "dur": 0.541, + "args": { + "External id": 1437346,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361808.100, "dur": 0.502, + "args": { + "External id": 1437347,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361810.431, "dur": 2.805, + "args": { + "External id": 1437348,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361814.934, "dur": 0.742, + "args": { + "External id": 1437349,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361817.692, "dur": 0.442, + "args": { + "External id": 1437350,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361819.544, "dur": 0.598, + "args": { + "External id": 1437351,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361821.822, "dur": 0.590, + "args": { + "External id": 1437352,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853361823.887, "dur": 0.516, + "args": { + "External id": 1437353,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853361839.339, "dur": 38.247, + "args": { + "External id": 1437354,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853361949.051, "dur": 487.870, + "args": { + "External id": 1437355,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853361995.283, "dur": 435.011, + "args": { + "External id": 1437356,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17648, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853362009.799, "dur": 413.068, + "args": { + "External id": 1437357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853362463.548, "dur": 3.027, + "args": { + "External id": 1437358,"Record function id": 0, "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": 17650, "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": 2338706, "tid": 2338706, + "ts": 6413853362574.396, "dur": 28792.748, + "args": { + "External id": 1437359,"Record function id": 0, "Ev Idx": 17651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362694.206, "dur": 7.503, + "args": { + "External id": 1437360,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362705.513, "dur": 1.107, + "args": { + "External id": 1437361,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362708.597, "dur": 3.204, + "args": { + "External id": 1437362,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362713.770, "dur": 1.060, + "args": { + "External id": 1437363,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362716.457, "dur": 1.138, + "args": { + "External id": 1437364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362719.024, "dur": 0.741, + "args": { + "External id": 1437365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362721.810, "dur": 0.934, + "args": { + "External id": 1437366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362724.677, "dur": 2.273, + "args": { + "External id": 1437367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362728.961, "dur": 1.034, + "args": { + "External id": 1437368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853362731.375, "dur": 0.798, + "args": { + "External id": 1437369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853362755.159, "dur": 28551.592, + "args": { + "External id": 1437370,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853362773.570, "dur": 28522.792, + "args": { + "External id": 1437371,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853362792.067, "dur": 17.904, + "args": { + "External id": 1437372,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853362813.874, "dur": 28439.918, + "args": { + "External id": 1437373,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853362817.004, "dur": 28436.108, + "args": { + "External id": 1437374,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853362821.508, "dur": 6.800, + "args": { + "External id": 1437375,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853362830.204, "dur": 28417.807, + "args": { + "External id": 1437376,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853391554.373, "dur": 44.466, + "args": { + "External id": 1437377,"Sequence number": 15348916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17669 + } + }, + { + "ph": "s", "id": 419, "pid": 2338706, "tid": 2338706, "ts": 6413853391554.373, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853391580.838, "dur": 12.618, + "args": { + "External id": 1437378,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853391586.559, "dur": 6.571, + "args": { + "External id": 1437379,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853391677.858, "dur": 84.060, + "args": { + "External id": 1437380,"Record function id": 0, "Ev Idx": 17672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853391763.686, "dur": 1352.026, + "args": { + "External id": 1437381,"Record function id": 0, "Ev Idx": 17673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853391813.220, "dur": 1282.650, + "args": { + "External id": 1437382,"Sequence number": 15348917, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17674 + } + }, + { + "ph": "s", "id": 418, "pid": 2338706, "tid": 2338706, "ts": 6413853391813.220, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853391894.037, "dur": 58.724, + "args": { + "External id": 1437383,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853391968.990, "dur": 172.477, + "args": { + "External id": 1437384,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853392163.844, "dur": 47.605, + "args": { + "External id": 1437385,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853392220.579, "dur": 36.389, + "args": { + "External id": 1437386,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853392292.420, "dur": 35.940, + "args": { + "External id": 1437387,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853392351.872, "dur": 22.298, + "args": { + "External id": 1437388,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853392400.551, "dur": 159.381, + "args": { + "External id": 1437389,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853392459.948, "dur": 15.259, + "args": { + "External id": 1437390,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853392467.148, "dur": 7.120, + "args": { + "External id": 1437391,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853392479.750, "dur": 4.479, + "args": { + "External id": 1437392,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853392486.115, "dur": 1.080, + "args": { + "External id": 1437393,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853392490.214, "dur": 6.508, + "args": { + "External id": 1437394,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853392575.824, "dur": 57.199, + "args": { + "External id": 1437395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853392665.970, "dur": 36.403, + "args": { + "External id": 1437396,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853392715.294, "dur": 50.813, + "args": { + "External id": 1437397,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853392777.531, "dur": 41.152, + "args": { + "External id": 1437398,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853392841.243, "dur": 33.365, + "args": { + "External id": 1437399,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853392882.072, "dur": 41.782, + "args": { + "External id": 1437400,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853392942.735, "dur": 20.202, + "args": { + "External id": 1437401,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17693 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 2338706, "tid": 2338706, + "ts": 6413853393192.728, "dur": 88.654, + "args": { + "External id": 1437402,"Record function id": 0, "Ev Idx": 17694 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853393368.019, "dur": 52.739, + "args": { + "External id": 1437403,"Record function id": 0, "Ev Idx": 17695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338706, "tid": 2338706, + "ts": 6413853393435.381, "dur": 29347.906, + "args": { + "External id": 1437404,"Record function id": 0, "Ev Idx": 17696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338706, "tid": 2338706, + "ts": 6413853393445.734, "dur": 1106.312, + "args": { + "External id": 1437405,"Record function id": 0, "Ev Idx": 17697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853393548.711, "dur": 11.439, + "args": { + "External id": 1437406,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853393577.452, "dur": 38.073, + "args": { + "External id": 1437407,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393584.599, "dur": 2.551, + "args": { + "External id": 1437408,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393589.778, "dur": 0.612, + "args": { + "External id": 1437409,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393592.706, "dur": 0.562, + "args": { + "External id": 1437410,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393594.543, "dur": 0.416, + "args": { + "External id": 1437411,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393596.965, "dur": 0.569, + "args": { + "External id": 1437412,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393599.120, "dur": 0.664, + "args": { + "External id": 1437413,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393601.606, "dur": 2.780, + "args": { + "External id": 1437414,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393605.915, "dur": 0.548, + "args": { + "External id": 1437415,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393608.534, "dur": 0.481, + "args": { + "External id": 1437416,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853393629.241, "dur": 63.365, + "args": { + "External id": 1437417,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853393730.909, "dur": 130.036, + "args": { + "External id": 1437418,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853393743.997, "dur": 4.046, + "args": { + "External id": 1437419,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853393753.797, "dur": 12.566, + "args": { + "External id": 1437420,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853393759.355, "dur": 6.520, + "args": { + "External id": 1437421,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393763.776, "dur": 0.786, + "args": { + "External id": 1437422,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853393774.413, "dur": 28.887, + "args": { + "External id": 1437423,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393776.862, "dur": 0.824, + "args": { + "External id": 1437424,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393779.289, "dur": 0.935, + "args": { + "External id": 1437425,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393781.925, "dur": 0.455, + "args": { + "External id": 1437426,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393784.302, "dur": 2.372, + "args": { + "External id": 1437427,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393788.266, "dur": 0.587, + "args": { + "External id": 1437428,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393790.680, "dur": 0.505, + "args": { + "External id": 1437429,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393792.760, "dur": 0.371, + "args": { + "External id": 1437430,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393795.180, "dur": 0.573, + "args": { + "External id": 1437431,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853393797.344, "dur": 0.523, + "args": { + "External id": 1437432,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853393817.257, "dur": 34.604, + "args": { + "External id": 1437433,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853393921.972, "dur": 512.168, + "args": { + "External id": 1437434,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853393948.823, "dur": 478.349, + "args": { + "External id": 1437435,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17727, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853393960.782, "dur": 458.643, + "args": { + "External id": 1437436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853394463.190, "dur": 2.830, + "args": { + "External id": 1437437,"Record function id": 0, "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": 17729, "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": 2338706, "tid": 2338706, + "ts": 6413853394577.489, "dur": 27941.264, + "args": { + "External id": 1437438,"Record function id": 0, "Ev Idx": 17730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394696.599, "dur": 7.318, + "args": { + "External id": 1437439,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394707.823, "dur": 1.241, + "args": { + "External id": 1437440,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394711.428, "dur": 3.897, + "args": { + "External id": 1437441,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394717.436, "dur": 1.099, + "args": { + "External id": 1437442,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394720.302, "dur": 1.017, + "args": { + "External id": 1437443,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394722.770, "dur": 1.146, + "args": { + "External id": 1437444,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394726.018, "dur": 0.776, + "args": { + "External id": 1437445,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394729.005, "dur": 2.645, + "args": { + "External id": 1437446,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394733.515, "dur": 0.859, + "args": { + "External id": 1437447,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853394736.033, "dur": 0.918, + "args": { + "External id": 1437448,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853394756.924, "dur": 27693.934, + "args": { + "External id": 1437449,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853394775.745, "dur": 27664.304, + "args": { + "External id": 1437450,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853394793.968, "dur": 19.180, + "args": { + "External id": 1437451,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853394817.176, "dur": 27576.177, + "args": { + "External id": 1437452,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853394820.035, "dur": 27572.359, + "args": { + "External id": 1437453,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853394824.676, "dur": 6.759, + "args": { + "External id": 1437454,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853394833.249, "dur": 27553.869, + "args": { + "External id": 1437455,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853422715.690, "dur": 37.206, + "args": { + "External id": 1437456,"Sequence number": 15348918, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17748 + } + }, + { + "ph": "s", "id": 417, "pid": 2338706, "tid": 2338706, "ts": 6413853422715.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853422733.876, "dur": 13.452, + "args": { + "External id": 1437457,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853422740.078, "dur": 6.960, + "args": { + "External id": 1437458,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853422829.834, "dur": 83.389, + "args": { + "External id": 1437459,"Record function id": 0, "Ev Idx": 17751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853422915.106, "dur": 1395.899, + "args": { + "External id": 1437460,"Record function id": 0, "Ev Idx": 17752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853422957.022, "dur": 1336.466, + "args": { + "External id": 1437461,"Sequence number": 15348919, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17753 + } + }, + { + "ph": "s", "id": 416, "pid": 2338706, "tid": 2338706, "ts": 6413853422957.022, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853423098.862, "dur": 78.238, + "args": { + "External id": 1437462,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853423205.333, "dur": 115.822, + "args": { + "External id": 1437463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853423339.059, "dur": 42.941, + "args": { + "External id": 1437464,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853423391.028, "dur": 35.337, + "args": { + "External id": 1437465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853423466.324, "dur": 33.167, + "args": { + "External id": 1437466,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853423524.367, "dur": 20.027, + "args": { + "External id": 1437467,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853423572.348, "dur": 164.310, + "args": { + "External id": 1437468,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853423634.612, "dur": 16.170, + "args": { + "External id": 1437469,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853423642.113, "dur": 7.549, + "args": { + "External id": 1437470,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853423655.206, "dur": 4.973, + "args": { + "External id": 1437471,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853423662.077, "dur": 1.542, + "args": { + "External id": 1437472,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853423666.576, "dur": 6.486, + "args": { + "External id": 1437473,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853423750.181, "dur": 54.337, + "args": { + "External id": 1437474,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853423838.055, "dur": 36.323, + "args": { + "External id": 1437475,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853423886.501, "dur": 48.986, + "args": { + "External id": 1437476,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853423946.629, "dur": 59.844, + "args": { + "External id": 1437477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853424034.459, "dur": 69.586, + "args": { + "External id": 1437478,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853424115.464, "dur": 48.433, + "args": { + "External id": 1437479,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853424186.719, "dur": 23.918, + "args": { + "External id": 1437480,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 2338706, "tid": 2338706, + "ts": 6413853424387.027, "dur": 93.649, + "args": { + "External id": 1437481,"Record function id": 0, "Ev Idx": 17773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853424571.610, "dur": 53.150, + "args": { + "External id": 1437482,"Record function id": 0, "Ev Idx": 17774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338706, "tid": 2338706, + "ts": 6413853424635.552, "dur": 31620.080, + "args": { + "External id": 1437483,"Record function id": 0, "Ev Idx": 17775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338706, "tid": 2338706, + "ts": 6413853424646.877, "dur": 1098.449, + "args": { + "External id": 1437484,"Record function id": 0, "Ev Idx": 17776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853424744.429, "dur": 10.314, + "args": { + "External id": 1437485,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853424769.805, "dur": 81.411, + "args": { + "External id": 1437486,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424776.625, "dur": 2.321, + "args": { + "External id": 1437487,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424782.399, "dur": 0.811, + "args": { + "External id": 1437488,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424784.660, "dur": 0.710, + "args": { + "External id": 1437489,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424787.209, "dur": 0.629, + "args": { + "External id": 1437490,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424789.576, "dur": 0.565, + "args": { + "External id": 1437491,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424831.090, "dur": 0.755, + "args": { + "External id": 1437492,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424833.650, "dur": 2.788, + "args": { + "External id": 1437493,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424838.771, "dur": 0.705, + "args": { + "External id": 1437494,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853424843.304, "dur": 0.773, + "args": { + "External id": 1437495,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853424864.665, "dur": 62.298, + "args": { + "External id": 1437496,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853424965.821, "dur": 213.492, + "args": { + "External id": 1437497,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853425006.131, "dur": 6.694, + "args": { + "External id": 1437498,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853425020.270, "dur": 13.155, + "args": { + "External id": 1437499,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853425025.576, "dur": 7.336, + "args": { + "External id": 1437500,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425030.136, "dur": 0.985, + "args": { + "External id": 1437501,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853425042.415, "dur": 66.504, + "args": { + "External id": 1437502,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425045.079, "dur": 0.639, + "args": { + "External id": 1437503,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425047.416, "dur": 0.484, + "args": { + "External id": 1437504,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425049.265, "dur": 0.520, + "args": { + "External id": 1437505,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425085.757, "dur": 4.435, + "args": { + "External id": 1437506,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425093.536, "dur": 0.642, + "args": { + "External id": 1437507,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425096.549, "dur": 0.727, + "args": { + "External id": 1437508,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425098.618, "dur": 0.448, + "args": { + "External id": 1437509,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425101.116, "dur": 0.473, + "args": { + "External id": 1437510,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853425103.030, "dur": 0.486, + "args": { + "External id": 1437511,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853425126.299, "dur": 42.915, + "args": { + "External id": 1437512,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853425247.665, "dur": 389.682, + "args": { + "External id": 1437513,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853425277.262, "dur": 354.560, + "args": { + "External id": 1437514,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17806, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853425289.840, "dur": 335.932, + "args": { + "External id": 1437515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853425662.282, "dur": 2.993, + "args": { + "External id": 1437516,"Record function id": 0, "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": 17808, "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": 2338706, "tid": 2338706, + "ts": 6413853425768.852, "dur": 30157.164, + "args": { + "External id": 1437517,"Record function id": 0, "Ev Idx": 17809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425884.630, "dur": 6.368, + "args": { + "External id": 1437518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425894.735, "dur": 1.061, + "args": { + "External id": 1437519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425897.614, "dur": 3.671, + "args": { + "External id": 1437520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425903.106, "dur": 0.840, + "args": { + "External id": 1437521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425905.653, "dur": 1.737, + "args": { + "External id": 1437522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425908.740, "dur": 1.027, + "args": { + "External id": 1437523,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425911.518, "dur": 0.747, + "args": { + "External id": 1437524,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425914.466, "dur": 2.465, + "args": { + "External id": 1437525,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425918.553, "dur": 0.885, + "args": { + "External id": 1437526,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853425921.554, "dur": 1.338, + "args": { + "External id": 1437527,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853425942.000, "dur": 29919.941, + "args": { + "External id": 1437528,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853425959.359, "dur": 29890.998, + "args": { + "External id": 1437529,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853425975.473, "dur": 38.792, + "args": { + "External id": 1437530,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853426022.817, "dur": 29781.886, + "args": { + "External id": 1437531,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853426026.099, "dur": 29777.052, + "args": { + "External id": 1437532,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853426030.830, "dur": 7.012, + "args": { + "External id": 1437533,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853426039.994, "dur": 29759.185, + "args": { + "External id": 1437534,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853456173.592, "dur": 46.988, + "args": { + "External id": 1437535,"Sequence number": 15348920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17827 + } + }, + { + "ph": "s", "id": 415, "pid": 2338706, "tid": 2338706, "ts": 6413853456173.592, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853456198.420, "dur": 15.258, + "args": { + "External id": 1437536,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853456204.420, "dur": 8.768, + "args": { + "External id": 1437537,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853456311.195, "dur": 88.563, + "args": { + "External id": 1437538,"Record function id": 0, "Ev Idx": 17830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853456401.255, "dur": 1354.086, + "args": { + "External id": 1437539,"Record function id": 0, "Ev Idx": 17831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853456447.586, "dur": 1291.014, + "args": { + "External id": 1437540,"Sequence number": 15348921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17832 + } + }, + { + "ph": "s", "id": 414, "pid": 2338706, "tid": 2338706, "ts": 6413853456447.586, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853456538.668, "dur": 63.071, + "args": { + "External id": 1437541,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853456620.127, "dur": 120.907, + "args": { + "External id": 1437542,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853456756.457, "dur": 42.350, + "args": { + "External id": 1437543,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853456806.389, "dur": 35.357, + "args": { + "External id": 1437544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853456878.165, "dur": 32.178, + "args": { + "External id": 1437545,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853456931.906, "dur": 23.191, + "args": { + "External id": 1437546,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853456997.488, "dur": 207.334, + "args": { + "External id": 1437547,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853457096.104, "dur": 16.237, + "args": { + "External id": 1437548,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853457103.412, "dur": 7.715, + "args": { + "External id": 1437549,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853457116.930, "dur": 5.059, + "args": { + "External id": 1437550,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853457123.608, "dur": 1.814, + "args": { + "External id": 1437551,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853457128.278, "dur": 7.449, + "args": { + "External id": 1437552,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853457220.776, "dur": 73.357, + "args": { + "External id": 1437553,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853457333.947, "dur": 41.098, + "args": { + "External id": 1437554,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853457388.083, "dur": 56.184, + "args": { + "External id": 1437555,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853457457.482, "dur": 45.094, + "args": { + "External id": 1437556,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853457527.282, "dur": 34.478, + "args": { + "External id": 1437557,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853457570.016, "dur": 44.727, + "args": { + "External id": 1437558,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853457635.398, "dur": 23.809, + "args": { + "External id": 1437559,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 2338706, "tid": 2338706, + "ts": 6413853457832.407, "dur": 90.771, + "args": { + "External id": 1437560,"Record function id": 0, "Ev Idx": 17852 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853458037.310, "dur": 100.879, + "args": { + "External id": 1437561,"Record function id": 0, "Ev Idx": 17853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338706, "tid": 2338706, + "ts": 6413853458152.049, "dur": 30078.205, + "args": { + "External id": 1437562,"Record function id": 0, "Ev Idx": 17854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338706, "tid": 2338706, + "ts": 6413853458164.148, "dur": 1062.368, + "args": { + "External id": 1437563,"Record function id": 0, "Ev Idx": 17855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853458264.612, "dur": 11.916, + "args": { + "External id": 1437564,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853458293.780, "dur": 38.166, + "args": { + "External id": 1437565,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458300.584, "dur": 2.691, + "args": { + "External id": 1437566,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458306.008, "dur": 0.721, + "args": { + "External id": 1437567,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458308.248, "dur": 0.500, + "args": { + "External id": 1437568,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458310.602, "dur": 0.557, + "args": { + "External id": 1437569,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458312.467, "dur": 0.707, + "args": { + "External id": 1437570,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458315.097, "dur": 0.665, + "args": { + "External id": 1437571,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458317.210, "dur": 3.312, + "args": { + "External id": 1437572,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458322.404, "dur": 0.752, + "args": { + "External id": 1437573,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458324.561, "dur": 0.503, + "args": { + "External id": 1437574,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853458345.357, "dur": 65.209, + "args": { + "External id": 1437575,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853458448.976, "dur": 133.811, + "args": { + "External id": 1437576,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853458463.749, "dur": 4.317, + "args": { + "External id": 1437577,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853458474.183, "dur": 12.655, + "args": { + "External id": 1437578,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853458479.351, "dur": 6.960, + "args": { + "External id": 1437579,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458484.130, "dur": 0.741, + "args": { + "External id": 1437580,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853458494.849, "dur": 27.017, + "args": { + "External id": 1437581,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458496.926, "dur": 0.822, + "args": { + "External id": 1437582,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458499.390, "dur": 0.601, + "args": { + "External id": 1437583,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458501.604, "dur": 0.504, + "args": { + "External id": 1437584,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458504.331, "dur": 2.872, + "args": { + "External id": 1437585,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458508.494, "dur": 0.441, + "args": { + "External id": 1437586,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458510.677, "dur": 0.452, + "args": { + "External id": 1437587,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458512.740, "dur": 0.551, + "args": { + "External id": 1437588,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458514.875, "dur": 0.623, + "args": { + "External id": 1437589,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853458517.019, "dur": 0.450, + "args": { + "External id": 1437590,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853458535.521, "dur": 37.801, + "args": { + "External id": 1437591,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853458647.424, "dur": 462.938, + "args": { + "External id": 1437592,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853458674.878, "dur": 428.620, + "args": { + "External id": 1437593,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17885, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853458686.614, "dur": 407.255, + "args": { + "External id": 1437594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853459138.363, "dur": 3.535, + "args": { + "External id": 1437595,"Record function id": 0, "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": 17887, "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": 2338706, "tid": 2338706, + "ts": 6413853459251.000, "dur": 28667.186, + "args": { + "External id": 1437596,"Record function id": 0, "Ev Idx": 17888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459371.275, "dur": 7.616, + "args": { + "External id": 1437597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459382.836, "dur": 1.475, + "args": { + "External id": 1437598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459386.375, "dur": 3.687, + "args": { + "External id": 1437599,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459392.058, "dur": 1.077, + "args": { + "External id": 1437600,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459394.772, "dur": 0.819, + "args": { + "External id": 1437601,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459397.239, "dur": 1.097, + "args": { + "External id": 1437602,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459400.091, "dur": 1.018, + "args": { + "External id": 1437603,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459403.442, "dur": 2.325, + "args": { + "External id": 1437604,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459407.310, "dur": 0.860, + "args": { + "External id": 1437605,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853459409.931, "dur": 0.980, + "args": { + "External id": 1437606,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853459434.353, "dur": 28422.656, + "args": { + "External id": 1437607,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853459453.146, "dur": 28392.709, + "args": { + "External id": 1437608,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853459471.090, "dur": 18.269, + "args": { + "External id": 1437609,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853459493.521, "dur": 28306.023, + "args": { + "External id": 1437610,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853459496.335, "dur": 28302.223, + "args": { + "External id": 1437611,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853459500.784, "dur": 6.096, + "args": { + "External id": 1437612,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853459508.722, "dur": 28285.209, + "args": { + "External id": 1437613,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853488152.467, "dur": 44.760, + "args": { + "External id": 1437614,"Sequence number": 15348922, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17906 + } + }, + { + "ph": "s", "id": 413, "pid": 2338706, "tid": 2338706, "ts": 6413853488152.467, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853488175.401, "dur": 14.985, + "args": { + "External id": 1437615,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853488181.221, "dur": 7.599, + "args": { + "External id": 1437616,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853488282.826, "dur": 85.970, + "args": { + "External id": 1437617,"Record function id": 0, "Ev Idx": 17909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853488370.308, "dur": 1358.343, + "args": { + "External id": 1437618,"Record function id": 0, "Ev Idx": 17910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853488416.833, "dur": 1294.728, + "args": { + "External id": 1437619,"Sequence number": 15348923, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17911 + } + }, + { + "ph": "s", "id": 412, "pid": 2338706, "tid": 2338706, "ts": 6413853488416.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853488507.582, "dur": 66.160, + "args": { + "External id": 1437620,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853488591.320, "dur": 119.832, + "args": { + "External id": 1437621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853488727.214, "dur": 44.885, + "args": { + "External id": 1437622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853488779.995, "dur": 38.302, + "args": { + "External id": 1437623,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853488852.873, "dur": 36.040, + "args": { + "External id": 1437624,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853488913.695, "dur": 22.487, + "args": { + "External id": 1437625,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853488960.354, "dur": 226.616, + "args": { + "External id": 1437626,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853489040.732, "dur": 54.497, + "args": { + "External id": 1437627,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853489048.021, "dur": 44.542, + "args": { + "External id": 1437628,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853489099.560, "dur": 5.435, + "args": { + "External id": 1437629,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853489106.395, "dur": 1.310, + "args": { + "External id": 1437630,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853489111.142, "dur": 6.404, + "args": { + "External id": 1437631,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853489204.757, "dur": 71.320, + "args": { + "External id": 1437632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853489316.640, "dur": 39.408, + "args": { + "External id": 1437633,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853489368.606, "dur": 52.908, + "args": { + "External id": 1437634,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853489434.597, "dur": 42.194, + "args": { + "External id": 1437635,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 17927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853489502.155, "dur": 35.747, + "args": { + "External id": 1437636,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 17928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853489545.440, "dur": 43.447, + "args": { + "External id": 1437637,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 17929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853489609.252, "dur": 22.028, + "args": { + "External id": 1437638,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 17930 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 2338706, "tid": 2338706, + "ts": 6413853489803.929, "dur": 92.725, + "args": { + "External id": 1437639,"Record function id": 0, "Ev Idx": 17931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853490005.287, "dur": 97.591, + "args": { + "External id": 1437640,"Record function id": 0, "Ev Idx": 17932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338706, "tid": 2338706, + "ts": 6413853490116.837, "dur": 30667.811, + "args": { + "External id": 1437641,"Record function id": 0, "Ev Idx": 17933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338706, "tid": 2338706, + "ts": 6413853490128.299, "dur": 1081.080, + "args": { + "External id": 1437642,"Record function id": 0, "Ev Idx": 17934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853490228.930, "dur": 12.002, + "args": { + "External id": 1437643,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853490257.904, "dur": 40.253, + "args": { + "External id": 1437644,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490265.158, "dur": 2.398, + "args": { + "External id": 1437645,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490270.322, "dur": 0.582, + "args": { + "External id": 1437646,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490272.426, "dur": 0.698, + "args": { + "External id": 1437647,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490275.446, "dur": 0.994, + "args": { + "External id": 1437648,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490278.236, "dur": 0.437, + "args": { + "External id": 1437649,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490280.626, "dur": 0.790, + "args": { + "External id": 1437650,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490282.976, "dur": 3.360, + "args": { + "External id": 1437651,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490288.180, "dur": 0.666, + "args": { + "External id": 1437652,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490290.502, "dur": 0.473, + "args": { + "External id": 1437653,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853490311.348, "dur": 66.971, + "args": { + "External id": 1437654,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853490423.606, "dur": 136.598, + "args": { + "External id": 1437655,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 17947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853490437.876, "dur": 4.515, + "args": { + "External id": 1437656,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853490448.868, "dur": 12.928, + "args": { + "External id": 1437657,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853490454.244, "dur": 7.035, + "args": { + "External id": 1437658,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 17950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490458.922, "dur": 0.885, + "args": { + "External id": 1437659,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 17951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853490469.544, "dur": 28.035, + "args": { + "External id": 1437660,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 17952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490472.034, "dur": 0.842, + "args": { + "External id": 1437661,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490474.488, "dur": 0.847, + "args": { + "External id": 1437662,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490476.836, "dur": 0.631, + "args": { + "External id": 1437663,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490479.164, "dur": 3.243, + "args": { + "External id": 1437664,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490484.050, "dur": 0.782, + "args": { + "External id": 1437665,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490486.436, "dur": 0.579, + "args": { + "External id": 1437666,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490488.292, "dur": 0.580, + "args": { + "External id": 1437667,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490490.748, "dur": 0.591, + "args": { + "External id": 1437668,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853490492.741, "dur": 0.567, + "args": { + "External id": 1437669,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 17961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853490510.222, "dur": 41.086, + "args": { + "External id": 1437670,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 17962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853490622.322, "dur": 467.918, + "args": { + "External id": 1437671,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 17963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853490654.129, "dur": 393.962, + "args": { + "External id": 1437672,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 17964, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853490666.132, "dur": 375.228, + "args": { + "External id": 1437673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 17965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853491120.447, "dur": 3.672, + "args": { + "External id": 1437674,"Record function id": 0, "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": 17966, "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": 2338706, "tid": 2338706, + "ts": 6413853491233.098, "dur": 29272.570, + "args": { + "External id": 1437675,"Record function id": 0, "Ev Idx": 17967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491349.817, "dur": 7.352, + "args": { + "External id": 1437676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 17968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491361.301, "dur": 1.391, + "args": { + "External id": 1437677,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491364.589, "dur": 3.967, + "args": { + "External id": 1437678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491370.440, "dur": 1.077, + "args": { + "External id": 1437679,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491373.062, "dur": 1.381, + "args": { + "External id": 1437680,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 17972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491376.073, "dur": 1.004, + "args": { + "External id": 1437681,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 17973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491378.822, "dur": 1.196, + "args": { + "External id": 1437682,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 17974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491382.600, "dur": 2.350, + "args": { + "External id": 1437683,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491386.836, "dur": 1.047, + "args": { + "External id": 1437684,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853491389.580, "dur": 0.937, + "args": { + "External id": 1437685,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 17977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853491412.586, "dur": 29025.269, + "args": { + "External id": 1437686,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853491431.083, "dur": 28995.170, + "args": { + "External id": 1437687,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 17979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853491447.197, "dur": 19.107, + "args": { + "External id": 1437688,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853491470.416, "dur": 28909.526, + "args": { + "External id": 1437689,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 17981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853491473.209, "dur": 28905.706, + "args": { + "External id": 1437690,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 17982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853491477.512, "dur": 5.701, + "args": { + "External id": 1437691,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853491485.005, "dur": 28888.623, + "args": { + "External id": 1437692,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 17984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853520704.359, "dur": 48.231, + "args": { + "External id": 1437693,"Sequence number": 15348924, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 17985 + } + }, + { + "ph": "s", "id": 411, "pid": 2338706, "tid": 2338706, "ts": 6413853520704.359, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853520732.463, "dur": 13.278, + "args": { + "External id": 1437694,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 17986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853520738.639, "dur": 6.858, + "args": { + "External id": 1437695,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 17987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853520837.210, "dur": 86.137, + "args": { + "External id": 1437696,"Record function id": 0, "Ev Idx": 17988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853520947.557, "dur": 1396.995, + "args": { + "External id": 1437697,"Record function id": 0, "Ev Idx": 17989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853521011.483, "dur": 1315.390, + "args": { + "External id": 1437698,"Sequence number": 15348925, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 17990 + } + }, + { + "ph": "s", "id": 410, "pid": 2338706, "tid": 2338706, "ts": 6413853521011.483, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853521150.574, "dur": 64.654, + "args": { + "External id": 1437699,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 17991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853521233.882, "dur": 119.316, + "args": { + "External id": 1437700,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 17992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853521370.763, "dur": 44.503, + "args": { + "External id": 1437701,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853521424.440, "dur": 35.717, + "args": { + "External id": 1437702,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 17994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853521491.137, "dur": 31.407, + "args": { + "External id": 1437703,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853521545.858, "dur": 21.238, + "args": { + "External id": 1437704,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 17996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853521592.756, "dur": 165.093, + "args": { + "External id": 1437705,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 17997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853521657.339, "dur": 15.418, + "args": { + "External id": 1437706,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 17998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853521664.612, "dur": 7.197, + "args": { + "External id": 1437707,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 17999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853521676.941, "dur": 5.029, + "args": { + "External id": 1437708,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853521683.352, "dur": 1.145, + "args": { + "External id": 1437709,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853521687.297, "dur": 5.691, + "args": { + "External id": 1437710,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853521773.600, "dur": 55.390, + "args": { + "External id": 1437711,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853521864.232, "dur": 38.740, + "args": { + "External id": 1437712,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853521915.753, "dur": 50.018, + "args": { + "External id": 1437713,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853521992.024, "dur": 51.120, + "args": { + "External id": 1437714,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853522108.390, "dur": 37.957, + "args": { + "External id": 1437715,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853522155.237, "dur": 49.354, + "args": { + "External id": 1437716,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853522225.366, "dur": 24.223, + "args": { + "External id": 1437717,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18009 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 2338706, "tid": 2338706, + "ts": 6413853522421.046, "dur": 89.250, + "args": { + "External id": 1437718,"Record function id": 0, "Ev Idx": 18010 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853522598.263, "dur": 52.365, + "args": { + "External id": 1437719,"Record function id": 0, "Ev Idx": 18011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338706, "tid": 2338706, + "ts": 6413853522661.992, "dur": 30915.259, + "args": { + "External id": 1437720,"Record function id": 0, "Ev Idx": 18012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338706, "tid": 2338706, + "ts": 6413853522672.256, "dur": 1079.015, + "args": { + "External id": 1437721,"Record function id": 0, "Ev Idx": 18013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853522769.474, "dur": 10.311, + "args": { + "External id": 1437722,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853522796.732, "dur": 37.817, + "args": { + "External id": 1437723,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522803.183, "dur": 2.453, + "args": { + "External id": 1437724,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522809.402, "dur": 0.579, + "args": { + "External id": 1437725,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522811.408, "dur": 0.486, + "args": { + "External id": 1437726,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522813.807, "dur": 0.621, + "args": { + "External id": 1437727,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522816.066, "dur": 0.719, + "args": { + "External id": 1437728,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522818.409, "dur": 0.825, + "args": { + "External id": 1437729,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522820.557, "dur": 2.972, + "args": { + "External id": 1437730,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522825.681, "dur": 0.680, + "args": { + "External id": 1437731,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853522827.796, "dur": 0.442, + "args": { + "External id": 1437732,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853522847.983, "dur": 64.407, + "args": { + "External id": 1437733,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853522952.185, "dur": 224.767, + "args": { + "External id": 1437734,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853522966.248, "dur": 4.060, + "args": { + "External id": 1437735,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853523008.655, "dur": 14.960, + "args": { + "External id": 1437736,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853523014.904, "dur": 8.237, + "args": { + "External id": 1437737,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523019.778, "dur": 1.112, + "args": { + "External id": 1437738,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853523033.428, "dur": 69.006, + "args": { + "External id": 1437739,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523035.747, "dur": 0.649, + "args": { + "External id": 1437740,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523038.486, "dur": 0.516, + "args": { + "External id": 1437741,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523040.688, "dur": 0.820, + "args": { + "External id": 1437742,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523043.516, "dur": 2.782, + "args": { + "External id": 1437743,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523047.806, "dur": 0.544, + "args": { + "External id": 1437744,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523050.061, "dur": 0.638, + "args": { + "External id": 1437745,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523089.490, "dur": 2.368, + "args": { + "External id": 1437746,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523094.836, "dur": 0.676, + "args": { + "External id": 1437747,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853523096.925, "dur": 0.524, + "args": { + "External id": 1437748,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853523123.271, "dur": 42.624, + "args": { + "External id": 1437749,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853523248.483, "dur": 397.143, + "args": { + "External id": 1437750,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853523283.560, "dur": 356.455, + "args": { + "External id": 1437751,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18043, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853523295.747, "dur": 338.019, + "args": { + "External id": 1437752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853523668.583, "dur": 2.351, + "args": { + "External id": 1437753,"Record function id": 0, "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": 18045, "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": 2338706, "tid": 2338706, + "ts": 6413853523775.335, "dur": 29524.186, + "args": { + "External id": 1437754,"Record function id": 0, "Ev Idx": 18046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523897.553, "dur": 6.660, + "args": { + "External id": 1437755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523907.980, "dur": 1.411, + "args": { + "External id": 1437756,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523911.466, "dur": 3.870, + "args": { + "External id": 1437757,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523917.220, "dur": 0.854, + "args": { + "External id": 1437758,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523919.919, "dur": 0.944, + "args": { + "External id": 1437759,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523922.266, "dur": 1.241, + "args": { + "External id": 1437760,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523925.460, "dur": 0.813, + "args": { + "External id": 1437761,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523928.653, "dur": 2.427, + "args": { + "External id": 1437762,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523932.838, "dur": 0.870, + "args": { + "External id": 1437763,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853523935.456, "dur": 0.947, + "args": { + "External id": 1437764,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853523958.575, "dur": 29273.232, + "args": { + "External id": 1437765,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853523997.355, "dur": 29222.186, + "args": { + "External id": 1437766,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853524047.936, "dur": 56.637, + "args": { + "External id": 1437767,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853524110.993, "dur": 29057.314, + "args": { + "External id": 1437768,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853524114.112, "dur": 29053.321, + "args": { + "External id": 1437769,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853524118.734, "dur": 7.914, + "args": { + "External id": 1437770,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853524128.562, "dur": 29033.614, + "args": { + "External id": 1437771,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853553497.314, "dur": 47.846, + "args": { + "External id": 1437772,"Sequence number": 15348926, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18064 + } + }, + { + "ph": "s", "id": 409, "pid": 2338706, "tid": 2338706, "ts": 6413853553497.314, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853553523.209, "dur": 15.213, + "args": { + "External id": 1437773,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853553529.038, "dur": 9.063, + "args": { + "External id": 1437774,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853553633.633, "dur": 86.108, + "args": { + "External id": 1437775,"Record function id": 0, "Ev Idx": 18067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853553721.391, "dur": 1418.913, + "args": { + "External id": 1437776,"Record function id": 0, "Ev Idx": 18068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853553770.441, "dur": 1351.344, + "args": { + "External id": 1437777,"Sequence number": 15348927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18069 + } + }, + { + "ph": "s", "id": 408, "pid": 2338706, "tid": 2338706, "ts": 6413853553770.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853553859.219, "dur": 62.738, + "args": { + "External id": 1437778,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853553939.560, "dur": 176.971, + "args": { + "External id": 1437779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853554139.535, "dur": 51.839, + "args": { + "External id": 1437780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853554199.472, "dur": 35.277, + "args": { + "External id": 1437781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853554276.117, "dur": 37.267, + "args": { + "External id": 1437782,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853554336.995, "dur": 24.089, + "args": { + "External id": 1437783,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853554386.807, "dur": 162.543, + "args": { + "External id": 1437784,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853554446.454, "dur": 15.279, + "args": { + "External id": 1437785,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853554453.294, "dur": 7.331, + "args": { + "External id": 1437786,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853554466.217, "dur": 5.170, + "args": { + "External id": 1437787,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853554472.783, "dur": 1.439, + "args": { + "External id": 1437788,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853554477.087, "dur": 7.809, + "args": { + "External id": 1437789,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853554563.806, "dur": 60.340, + "args": { + "External id": 1437790,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853554660.627, "dur": 35.949, + "args": { + "External id": 1437791,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853554708.756, "dur": 53.968, + "args": { + "External id": 1437792,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853554775.853, "dur": 46.032, + "args": { + "External id": 1437793,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853554846.661, "dur": 34.491, + "args": { + "External id": 1437794,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853554889.681, "dur": 46.334, + "args": { + "External id": 1437795,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853554955.728, "dur": 42.225, + "args": { + "External id": 1437796,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18088 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 2338706, "tid": 2338706, + "ts": 6413853555217.411, "dur": 97.556, + "args": { + "External id": 1437797,"Record function id": 0, "Ev Idx": 18089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853555401.913, "dur": 52.942, + "args": { + "External id": 1437798,"Record function id": 0, "Ev Idx": 18090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338706, "tid": 2338706, + "ts": 6413853555466.426, "dur": 30336.906, + "args": { + "External id": 1437799,"Record function id": 0, "Ev Idx": 18091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338706, "tid": 2338706, + "ts": 6413853555477.363, "dur": 1072.647, + "args": { + "External id": 1437800,"Record function id": 0, "Ev Idx": 18092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853555577.348, "dur": 11.421, + "args": { + "External id": 1437801,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853555605.561, "dur": 38.091, + "args": { + "External id": 1437802,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555612.330, "dur": 2.593, + "args": { + "External id": 1437803,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555618.032, "dur": 0.745, + "args": { + "External id": 1437804,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555620.257, "dur": 0.575, + "args": { + "External id": 1437805,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555622.808, "dur": 0.645, + "args": { + "External id": 1437806,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555625.008, "dur": 0.513, + "args": { + "External id": 1437807,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555627.511, "dur": 0.744, + "args": { + "External id": 1437808,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555629.593, "dur": 2.864, + "args": { + "External id": 1437809,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555634.293, "dur": 0.448, + "args": { + "External id": 1437810,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555636.262, "dur": 0.443, + "args": { + "External id": 1437811,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853555656.553, "dur": 66.357, + "args": { + "External id": 1437812,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853555762.143, "dur": 138.916, + "args": { + "External id": 1437813,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853555776.564, "dur": 4.466, + "args": { + "External id": 1437814,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853555787.081, "dur": 17.148, + "args": { + "External id": 1437815,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853555792.547, "dur": 11.177, + "args": { + "External id": 1437816,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555801.618, "dur": 0.598, + "args": { + "External id": 1437817,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853555811.808, "dur": 27.548, + "args": { + "External id": 1437818,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555814.138, "dur": 0.878, + "args": { + "External id": 1437819,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555817.023, "dur": 0.689, + "args": { + "External id": 1437820,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555819.068, "dur": 0.529, + "args": { + "External id": 1437821,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555821.423, "dur": 2.858, + "args": { + "External id": 1437822,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555825.636, "dur": 0.520, + "args": { + "External id": 1437823,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555828.141, "dur": 0.671, + "args": { + "External id": 1437824,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555830.060, "dur": 0.478, + "args": { + "External id": 1437825,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555832.277, "dur": 0.513, + "args": { + "External id": 1437826,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853555834.283, "dur": 0.449, + "args": { + "External id": 1437827,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853555850.361, "dur": 41.043, + "args": { + "External id": 1437828,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853555959.453, "dur": 472.400, + "args": { + "External id": 1437829,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853556009.723, "dur": 412.179, + "args": { + "External id": 1437830,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18122, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853556023.217, "dur": 391.580, + "args": { + "External id": 1437831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853556461.729, "dur": 2.549, + "args": { + "External id": 1437832,"Record function id": 0, "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": 18124, "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": 2338706, "tid": 2338706, + "ts": 6413853556574.970, "dur": 28968.591, + "args": { + "External id": 1437833,"Record function id": 0, "Ev Idx": 18125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556690.307, "dur": 7.561, + "args": { + "External id": 1437834,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556702.027, "dur": 1.061, + "args": { + "External id": 1437835,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556704.990, "dur": 3.490, + "args": { + "External id": 1437836,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556710.198, "dur": 0.926, + "args": { + "External id": 1437837,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556712.565, "dur": 0.932, + "args": { + "External id": 1437838,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556715.086, "dur": 0.858, + "args": { + "External id": 1437839,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556717.495, "dur": 1.028, + "args": { + "External id": 1437840,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556720.510, "dur": 2.391, + "args": { + "External id": 1437841,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556724.475, "dur": 1.019, + "args": { + "External id": 1437842,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853556727.649, "dur": 0.753, + "args": { + "External id": 1437843,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853556747.751, "dur": 28735.926, + "args": { + "External id": 1437844,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853556766.205, "dur": 28705.935, + "args": { + "External id": 1437845,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853556785.345, "dur": 18.966, + "args": { + "External id": 1437846,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853556811.079, "dur": 28615.259, + "args": { + "External id": 1437847,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853556814.138, "dur": 28611.282, + "args": { + "External id": 1437848,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853556818.567, "dur": 6.912, + "args": { + "External id": 1437849,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853556827.389, "dur": 28592.938, + "args": { + "External id": 1437850,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853585727.953, "dur": 42.385, + "args": { + "External id": 1437851,"Sequence number": 15348928, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18143 + } + }, + { + "ph": "s", "id": 407, "pid": 2338706, "tid": 2338706, "ts": 6413853585727.953, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853585750.989, "dur": 12.931, + "args": { + "External id": 1437852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853585756.930, "dur": 6.719, + "args": { + "External id": 1437853,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853585858.969, "dur": 101.576, + "args": { + "External id": 1437854,"Record function id": 0, "Ev Idx": 18146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853585963.178, "dur": 1474.786, + "args": { + "External id": 1437855,"Record function id": 0, "Ev Idx": 18147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853586098.950, "dur": 1320.913, + "args": { + "External id": 1437856,"Sequence number": 15348929, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18148 + } + }, + { + "ph": "s", "id": 406, "pid": 2338706, "tid": 2338706, "ts": 6413853586098.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853586197.799, "dur": 65.554, + "args": { + "External id": 1437857,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853586280.208, "dur": 120.642, + "args": { + "External id": 1437858,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853586417.436, "dur": 44.348, + "args": { + "External id": 1437859,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853586470.213, "dur": 39.281, + "args": { + "External id": 1437860,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853586543.238, "dur": 32.985, + "args": { + "External id": 1437861,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853586599.467, "dur": 23.822, + "args": { + "External id": 1437862,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853586651.218, "dur": 164.637, + "args": { + "External id": 1437863,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853586712.917, "dur": 16.309, + "args": { + "External id": 1437864,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853586720.286, "dur": 7.974, + "args": { + "External id": 1437865,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853586733.625, "dur": 4.877, + "args": { + "External id": 1437866,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853586739.867, "dur": 1.292, + "args": { + "External id": 1437867,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853586744.203, "dur": 7.738, + "args": { + "External id": 1437868,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853586829.438, "dur": 61.522, + "args": { + "External id": 1437869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853586926.693, "dur": 38.887, + "args": { + "External id": 1437870,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853587005.621, "dur": 105.203, + "args": { + "External id": 1437871,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853587128.729, "dur": 48.433, + "args": { + "External id": 1437872,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853587205.076, "dur": 38.742, + "args": { + "External id": 1437873,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853587251.733, "dur": 43.932, + "args": { + "External id": 1437874,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853587315.461, "dur": 23.229, + "args": { + "External id": 1437875,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18167 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 2338706, "tid": 2338706, + "ts": 6413853587515.518, "dur": 92.701, + "args": { + "External id": 1437876,"Record function id": 0, "Ev Idx": 18168 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853587697.454, "dur": 55.255, + "args": { + "External id": 1437877,"Record function id": 0, "Ev Idx": 18169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338706, "tid": 2338706, + "ts": 6413853587764.543, "dur": 28825.380, + "args": { + "External id": 1437878,"Record function id": 0, "Ev Idx": 18170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338706, "tid": 2338706, + "ts": 6413853587774.319, "dur": 1156.483, + "args": { + "External id": 1437879,"Record function id": 0, "Ev Idx": 18171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853587876.073, "dur": 10.397, + "args": { + "External id": 1437880,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853587903.215, "dur": 37.730, + "args": { + "External id": 1437881,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587909.732, "dur": 2.405, + "args": { + "External id": 1437882,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587915.145, "dur": 0.610, + "args": { + "External id": 1437883,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587917.377, "dur": 0.677, + "args": { + "External id": 1437884,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587920.230, "dur": 0.555, + "args": { + "External id": 1437885,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587922.194, "dur": 0.632, + "args": { + "External id": 1437886,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587924.706, "dur": 0.746, + "args": { + "External id": 1437887,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587927.092, "dur": 2.920, + "args": { + "External id": 1437888,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587932.163, "dur": 0.386, + "args": { + "External id": 1437889,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853587933.954, "dur": 0.667, + "args": { + "External id": 1437890,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853587954.943, "dur": 88.158, + "args": { + "External id": 1437891,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853588130.171, "dur": 151.469, + "args": { + "External id": 1437892,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853588144.906, "dur": 7.119, + "args": { + "External id": 1437893,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853588163.701, "dur": 14.144, + "args": { + "External id": 1437894,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853588169.116, "dur": 8.195, + "args": { + "External id": 1437895,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588173.846, "dur": 1.221, + "args": { + "External id": 1437896,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853588185.839, "dur": 27.499, + "args": { + "External id": 1437897,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588188.630, "dur": 0.562, + "args": { + "External id": 1437898,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588191.254, "dur": 0.571, + "args": { + "External id": 1437899,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588193.359, "dur": 0.578, + "args": { + "External id": 1437900,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588195.960, "dur": 2.410, + "args": { + "External id": 1437901,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588199.812, "dur": 0.498, + "args": { + "External id": 1437902,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588202.392, "dur": 0.448, + "args": { + "External id": 1437903,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588204.186, "dur": 0.599, + "args": { + "External id": 1437904,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588206.555, "dur": 0.580, + "args": { + "External id": 1437905,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853588208.412, "dur": 0.419, + "args": { + "External id": 1437906,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853588229.495, "dur": 41.860, + "args": { + "External id": 1437907,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853588349.520, "dur": 476.444, + "args": { + "External id": 1437908,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853588379.858, "dur": 439.975, + "args": { + "External id": 1437909,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18201, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853588394.306, "dur": 415.548, + "args": { + "External id": 1437910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853588851.246, "dur": 2.441, + "args": { + "External id": 1437911,"Record function id": 0, "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": 18203, "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": 2338706, "tid": 2338706, + "ts": 6413853588955.199, "dur": 27354.298, + "args": { + "External id": 1437912,"Record function id": 0, "Ev Idx": 18204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589141.636, "dur": 8.289, + "args": { + "External id": 1437913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589154.309, "dur": 1.367, + "args": { + "External id": 1437914,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589157.551, "dur": 4.002, + "args": { + "External id": 1437915,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589163.725, "dur": 1.006, + "args": { + "External id": 1437916,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589166.447, "dur": 0.989, + "args": { + "External id": 1437917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589168.951, "dur": 0.869, + "args": { + "External id": 1437918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589171.657, "dur": 0.885, + "args": { + "External id": 1437919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589174.945, "dur": 2.277, + "args": { + "External id": 1437920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589178.681, "dur": 0.935, + "args": { + "External id": 1437921,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853589181.458, "dur": 0.851, + "args": { + "External id": 1437922,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853589203.372, "dur": 27038.871, + "args": { + "External id": 1437923,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853589222.115, "dur": 27008.395, + "args": { + "External id": 1437924,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853589262.822, "dur": 19.849, + "args": { + "External id": 1437925,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853589289.194, "dur": 26892.465, + "args": { + "External id": 1437926,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853589292.308, "dur": 26888.587, + "args": { + "External id": 1437927,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853589303.500, "dur": 6.550, + "args": { + "External id": 1437928,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853589311.799, "dur": 26863.875, + "args": { + "External id": 1437929,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853616509.755, "dur": 43.414, + "args": { + "External id": 1437930,"Sequence number": 15348930, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18222 + } + }, + { + "ph": "s", "id": 405, "pid": 2338706, "tid": 2338706, "ts": 6413853616509.755, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853616532.594, "dur": 13.743, + "args": { + "External id": 1437931,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853616538.694, "dur": 7.368, + "args": { + "External id": 1437932,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853616640.396, "dur": 86.779, + "args": { + "External id": 1437933,"Record function id": 0, "Ev Idx": 18225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853616729.141, "dur": 1405.317, + "args": { + "External id": 1437934,"Record function id": 0, "Ev Idx": 18226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853616778.354, "dur": 1337.677, + "args": { + "External id": 1437935,"Sequence number": 15348931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18227 + } + }, + { + "ph": "s", "id": 404, "pid": 2338706, "tid": 2338706, "ts": 6413853616778.354, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853616868.353, "dur": 62.534, + "args": { + "External id": 1437936,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853616948.143, "dur": 180.993, + "args": { + "External id": 1437937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853617151.274, "dur": 50.478, + "args": { + "External id": 1437938,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853617211.181, "dur": 34.894, + "args": { + "External id": 1437939,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853617286.674, "dur": 36.682, + "args": { + "External id": 1437940,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853617344.044, "dur": 23.534, + "args": { + "External id": 1437941,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853617394.738, "dur": 160.412, + "args": { + "External id": 1437942,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853617454.002, "dur": 15.503, + "args": { + "External id": 1437943,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853617461.237, "dur": 7.205, + "args": { + "External id": 1437944,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853617474.066, "dur": 5.393, + "args": { + "External id": 1437945,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853617480.765, "dur": 1.335, + "args": { + "External id": 1437946,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853617485.739, "dur": 6.769, + "args": { + "External id": 1437947,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853617569.144, "dur": 58.755, + "args": { + "External id": 1437948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853617663.596, "dur": 39.200, + "args": { + "External id": 1437949,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853617715.058, "dur": 52.058, + "args": { + "External id": 1437950,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853617780.169, "dur": 42.341, + "args": { + "External id": 1437951,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853617848.780, "dur": 31.668, + "args": { + "External id": 1437952,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853617888.063, "dur": 43.886, + "args": { + "External id": 1437953,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853617951.666, "dur": 22.935, + "args": { + "External id": 1437954,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18246 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 2338706, "tid": 2338706, + "ts": 6413853618214.608, "dur": 95.057, + "args": { + "External id": 1437955,"Record function id": 0, "Ev Idx": 18247 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853618399.159, "dur": 55.971, + "args": { + "External id": 1437956,"Record function id": 0, "Ev Idx": 18248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338706, "tid": 2338706, + "ts": 6413853618467.144, "dur": 31271.833, + "args": { + "External id": 1437957,"Record function id": 0, "Ev Idx": 18249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338706, "tid": 2338706, + "ts": 6413853618477.895, "dur": 1087.870, + "args": { + "External id": 1437958,"Record function id": 0, "Ev Idx": 18250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853618576.869, "dur": 11.387, + "args": { + "External id": 1437959,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853618605.744, "dur": 37.753, + "args": { + "External id": 1437960,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618612.327, "dur": 2.490, + "args": { + "External id": 1437961,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618617.906, "dur": 0.769, + "args": { + "External id": 1437962,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618619.980, "dur": 0.746, + "args": { + "External id": 1437963,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618622.973, "dur": 0.715, + "args": { + "External id": 1437964,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618625.206, "dur": 0.483, + "args": { + "External id": 1437965,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618627.524, "dur": 0.568, + "args": { + "External id": 1437966,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618629.567, "dur": 3.256, + "args": { + "External id": 1437967,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618635.107, "dur": 0.658, + "args": { + "External id": 1437968,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618636.978, "dur": 0.449, + "args": { + "External id": 1437969,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853618656.982, "dur": 66.430, + "args": { + "External id": 1437970,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853618764.565, "dur": 138.822, + "args": { + "External id": 1437971,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853618778.685, "dur": 4.550, + "args": { + "External id": 1437972,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853618790.347, "dur": 13.170, + "args": { + "External id": 1437973,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853618796.049, "dur": 6.962, + "args": { + "External id": 1437974,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618800.515, "dur": 0.922, + "args": { + "External id": 1437975,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853618811.251, "dur": 31.520, + "args": { + "External id": 1437976,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618813.671, "dur": 0.648, + "args": { + "External id": 1437977,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618816.483, "dur": 0.553, + "args": { + "External id": 1437978,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618818.540, "dur": 0.514, + "args": { + "External id": 1437979,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618821.224, "dur": 2.776, + "args": { + "External id": 1437980,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618829.658, "dur": 0.407, + "args": { + "External id": 1437981,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618832.091, "dur": 0.566, + "args": { + "External id": 1437982,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618833.826, "dur": 0.452, + "args": { + "External id": 1437983,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618836.135, "dur": 0.610, + "args": { + "External id": 1437984,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853618837.941, "dur": 0.690, + "args": { + "External id": 1437985,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853618856.372, "dur": 37.364, + "args": { + "External id": 1437986,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853618964.136, "dur": 482.575, + "args": { + "External id": 1437987,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853619015.626, "dur": 423.970, + "args": { + "External id": 1437988,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18280, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853619029.441, "dur": 402.983, + "args": { + "External id": 1437989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853619476.180, "dur": 2.957, + "args": { + "External id": 1437990,"Record function id": 0, "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": 18282, "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": 2338706, "tid": 2338706, + "ts": 6413853619591.096, "dur": 29872.165, + "args": { + "External id": 1437991,"Record function id": 0, "Ev Idx": 18283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619709.011, "dur": 7.482, + "args": { + "External id": 1437992,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619720.523, "dur": 1.305, + "args": { + "External id": 1437993,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619723.628, "dur": 4.036, + "args": { + "External id": 1437994,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619729.824, "dur": 0.861, + "args": { + "External id": 1437995,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619732.332, "dur": 0.767, + "args": { + "External id": 1437996,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619734.415, "dur": 0.848, + "args": { + "External id": 1437997,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619736.951, "dur": 1.135, + "args": { + "External id": 1437998,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619740.348, "dur": 2.334, + "args": { + "External id": 1437999,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619744.606, "dur": 0.985, + "args": { + "External id": 1438000,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853619747.464, "dur": 0.935, + "args": { + "External id": 1438001,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853619767.660, "dur": 29626.337, + "args": { + "External id": 1438002,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853619786.425, "dur": 29596.184, + "args": { + "External id": 1438003,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853619803.675, "dur": 19.070, + "args": { + "External id": 1438004,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853619829.204, "dur": 29505.008, + "args": { + "External id": 1438005,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853619832.052, "dur": 29501.001, + "args": { + "External id": 1438006,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853619836.516, "dur": 5.757, + "args": { + "External id": 1438007,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853619844.131, "dur": 29483.183, + "args": { + "External id": 1438008,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853649653.685, "dur": 48.041, + "args": { + "External id": 1438009,"Sequence number": 15348932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18301 + } + }, + { + "ph": "s", "id": 403, "pid": 2338706, "tid": 2338706, "ts": 6413853649653.685, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853649681.691, "dur": 13.455, + "args": { + "External id": 1438010,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853649687.661, "dur": 7.230, + "args": { + "External id": 1438011,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853649792.253, "dur": 84.082, + "args": { + "External id": 1438012,"Record function id": 0, "Ev Idx": 18304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853649878.696, "dur": 1405.204, + "args": { + "External id": 1438013,"Record function id": 0, "Ev Idx": 18305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853649927.639, "dur": 1338.809, + "args": { + "External id": 1438014,"Sequence number": 15348933, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18306 + } + }, + { + "ph": "s", "id": 402, "pid": 2338706, "tid": 2338706, "ts": 6413853649927.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853650035.334, "dur": 98.639, + "args": { + "External id": 1438015,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853650155.822, "dur": 117.059, + "args": { + "External id": 1438016,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853650289.917, "dur": 42.993, + "args": { + "External id": 1438017,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853650341.260, "dur": 35.832, + "args": { + "External id": 1438018,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853650412.512, "dur": 33.757, + "args": { + "External id": 1438019,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853650469.993, "dur": 23.000, + "args": { + "External id": 1438020,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853650518.236, "dur": 159.632, + "args": { + "External id": 1438021,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853650577.603, "dur": 15.939, + "args": { + "External id": 1438022,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853650585.134, "dur": 7.436, + "args": { + "External id": 1438023,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853650598.132, "dur": 5.295, + "args": { + "External id": 1438024,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853650605.014, "dur": 1.200, + "args": { + "External id": 1438025,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853650609.427, "dur": 6.155, + "args": { + "External id": 1438026,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853650691.964, "dur": 59.030, + "args": { + "External id": 1438027,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853650786.481, "dur": 36.991, + "args": { + "External id": 1438028,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853650835.691, "dur": 54.094, + "args": { + "External id": 1438029,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853650902.414, "dur": 44.014, + "args": { + "External id": 1438030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853650971.550, "dur": 54.578, + "args": { + "External id": 1438031,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853651037.338, "dur": 95.323, + "args": { + "External id": 1438032,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853651158.642, "dur": 26.116, + "args": { + "External id": 1438033,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 2338706, "tid": 2338706, + "ts": 6413853651359.752, "dur": 95.658, + "args": { + "External id": 1438034,"Record function id": 0, "Ev Idx": 18326 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853651545.321, "dur": 53.901, + "args": { + "External id": 1438035,"Record function id": 0, "Ev Idx": 18327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338706, "tid": 2338706, + "ts": 6413853651611.035, "dur": 31130.345, + "args": { + "External id": 1438036,"Record function id": 0, "Ev Idx": 18328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338706, "tid": 2338706, + "ts": 6413853651620.485, "dur": 1097.966, + "args": { + "External id": 1438037,"Record function id": 0, "Ev Idx": 18329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853651721.141, "dur": 10.722, + "args": { + "External id": 1438038,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853651748.920, "dur": 42.898, + "args": { + "External id": 1438039,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651755.590, "dur": 2.410, + "args": { + "External id": 1438040,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651761.605, "dur": 0.782, + "args": { + "External id": 1438041,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651764.444, "dur": 0.534, + "args": { + "External id": 1438042,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651767.222, "dur": 0.598, + "args": { + "External id": 1438043,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651769.502, "dur": 0.924, + "args": { + "External id": 1438044,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651772.519, "dur": 0.585, + "args": { + "External id": 1438045,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651778.320, "dur": 2.646, + "args": { + "External id": 1438046,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651782.933, "dur": 0.441, + "args": { + "External id": 1438047,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651785.101, "dur": 0.308, + "args": { + "External id": 1438048,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853651806.148, "dur": 66.633, + "args": { + "External id": 1438049,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853651911.019, "dur": 209.227, + "args": { + "External id": 1438050,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853651925.944, "dur": 4.155, + "args": { + "External id": 1438051,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853651936.295, "dur": 11.981, + "args": { + "External id": 1438052,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853651941.409, "dur": 6.360, + "args": { + "External id": 1438053,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651945.577, "dur": 0.730, + "args": { + "External id": 1438054,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853651955.869, "dur": 50.969, + "args": { + "External id": 1438055,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651958.237, "dur": 0.745, + "args": { + "External id": 1438056,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651960.800, "dur": 0.820, + "args": { + "External id": 1438057,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651963.853, "dur": 0.486, + "args": { + "External id": 1438058,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651966.587, "dur": 2.733, + "args": { + "External id": 1438059,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651970.714, "dur": 0.439, + "args": { + "External id": 1438060,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651973.523, "dur": 0.492, + "args": { + "External id": 1438061,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651975.610, "dur": 0.418, + "args": { + "External id": 1438062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853651997.425, "dur": 0.843, + "args": { + "External id": 1438063,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853652001.526, "dur": 0.442, + "args": { + "External id": 1438064,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853652022.391, "dur": 85.216, + "args": { + "External id": 1438065,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853652190.281, "dur": 419.489, + "args": { + "External id": 1438066,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853652220.724, "dur": 382.588, + "args": { + "External id": 1438067,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18359, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853652233.115, "dur": 363.336, + "args": { + "External id": 1438068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853652635.763, "dur": 2.412, + "args": { + "External id": 1438069,"Record function id": 0, "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": 18361, "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": 2338706, "tid": 2338706, + "ts": 6413853652742.610, "dur": 29722.379, + "args": { + "External id": 1438070,"Record function id": 0, "Ev Idx": 18362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652857.587, "dur": 7.414, + "args": { + "External id": 1438071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652869.514, "dur": 1.116, + "args": { + "External id": 1438072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652872.677, "dur": 4.540, + "args": { + "External id": 1438073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652879.151, "dur": 0.973, + "args": { + "External id": 1438074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652881.924, "dur": 1.145, + "args": { + "External id": 1438075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652884.494, "dur": 0.876, + "args": { + "External id": 1438076,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652887.059, "dur": 0.785, + "args": { + "External id": 1438077,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652889.937, "dur": 2.017, + "args": { + "External id": 1438078,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652893.631, "dur": 0.910, + "args": { + "External id": 1438079,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853652896.323, "dur": 0.851, + "args": { + "External id": 1438080,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853652920.496, "dur": 29476.868, + "args": { + "External id": 1438081,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853652940.289, "dur": 29445.381, + "args": { + "External id": 1438082,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853652956.935, "dur": 18.765, + "args": { + "External id": 1438083,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853652998.111, "dur": 29339.786, + "args": { + "External id": 1438084,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853653002.238, "dur": 29334.858, + "args": { + "External id": 1438085,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853653006.779, "dur": 7.789, + "args": { + "External id": 1438086,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853653016.691, "dur": 29315.192, + "args": { + "External id": 1438087,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853682661.171, "dur": 46.169, + "args": { + "External id": 1438088,"Sequence number": 15348934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18380 + } + }, + { + "ph": "s", "id": 401, "pid": 2338706, "tid": 2338706, "ts": 6413853682661.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853682686.151, "dur": 15.418, + "args": { + "External id": 1438089,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853682692.583, "dur": 7.590, + "args": { + "External id": 1438090,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853682794.038, "dur": 86.293, + "args": { + "External id": 1438091,"Record function id": 0, "Ev Idx": 18383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853682882.163, "dur": 1383.478, + "args": { + "External id": 1438092,"Record function id": 0, "Ev Idx": 18384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853682929.601, "dur": 1319.412, + "args": { + "External id": 1438093,"Sequence number": 15348935, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18385 + } + }, + { + "ph": "s", "id": 400, "pid": 2338706, "tid": 2338706, "ts": 6413853682929.601, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853683035.503, "dur": 101.634, + "args": { + "External id": 1438094,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853683157.704, "dur": 117.446, + "args": { + "External id": 1438095,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853683291.451, "dur": 43.549, + "args": { + "External id": 1438096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853683343.524, "dur": 35.317, + "args": { + "External id": 1438097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853683414.115, "dur": 32.040, + "args": { + "External id": 1438098,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853683469.356, "dur": 19.685, + "args": { + "External id": 1438099,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853683515.768, "dur": 159.811, + "args": { + "External id": 1438100,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853683574.882, "dur": 16.185, + "args": { + "External id": 1438101,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853683582.613, "dur": 7.445, + "args": { + "External id": 1438102,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853683595.315, "dur": 5.222, + "args": { + "External id": 1438103,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853683602.154, "dur": 1.569, + "args": { + "External id": 1438104,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853683606.747, "dur": 7.746, + "args": { + "External id": 1438105,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853683688.583, "dur": 55.975, + "args": { + "External id": 1438106,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853683780.434, "dur": 36.023, + "args": { + "External id": 1438107,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853683828.596, "dur": 53.627, + "args": { + "External id": 1438108,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853683894.311, "dur": 42.566, + "args": { + "External id": 1438109,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853683961.271, "dur": 52.632, + "args": { + "External id": 1438110,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853684024.656, "dur": 91.741, + "args": { + "External id": 1438111,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853684142.540, "dur": 24.788, + "args": { + "External id": 1438112,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18404 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 2338706, "tid": 2338706, + "ts": 6413853684341.374, "dur": 88.323, + "args": { + "External id": 1438113,"Record function id": 0, "Ev Idx": 18405 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853684515.069, "dur": 52.996, + "args": { + "External id": 1438114,"Record function id": 0, "Ev Idx": 18406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338706, "tid": 2338706, + "ts": 6413853684579.208, "dur": 32148.044, + "args": { + "External id": 1438115,"Record function id": 0, "Ev Idx": 18407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338706, "tid": 2338706, + "ts": 6413853684590.376, "dur": 1068.650, + "args": { + "External id": 1438116,"Record function id": 0, "Ev Idx": 18408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853684685.436, "dur": 10.577, + "args": { + "External id": 1438117,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853684713.523, "dur": 39.359, + "args": { + "External id": 1438118,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684720.549, "dur": 2.473, + "args": { + "External id": 1438119,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684726.671, "dur": 0.548, + "args": { + "External id": 1438120,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684728.774, "dur": 0.850, + "args": { + "External id": 1438121,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684732.247, "dur": 0.741, + "args": { + "External id": 1438122,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684734.402, "dur": 0.640, + "args": { + "External id": 1438123,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684736.925, "dur": 0.773, + "args": { + "External id": 1438124,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684739.297, "dur": 3.110, + "args": { + "External id": 1438125,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684744.140, "dur": 0.680, + "args": { + "External id": 1438126,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684746.160, "dur": 0.407, + "args": { + "External id": 1438127,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853684766.618, "dur": 62.861, + "args": { + "External id": 1438128,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853684866.984, "dur": 169.117, + "args": { + "External id": 1438129,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853684880.892, "dur": 4.052, + "args": { + "External id": 1438130,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853684891.345, "dur": 13.027, + "args": { + "External id": 1438131,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853684896.911, "dur": 6.962, + "args": { + "External id": 1438132,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684901.617, "dur": 0.864, + "args": { + "External id": 1438133,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853684912.296, "dur": 29.104, + "args": { + "External id": 1438134,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684914.426, "dur": 0.796, + "args": { + "External id": 1438135,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684917.048, "dur": 0.998, + "args": { + "External id": 1438136,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684919.686, "dur": 0.661, + "args": { + "External id": 1438137,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684922.212, "dur": 3.493, + "args": { + "External id": 1438138,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684927.028, "dur": 0.599, + "args": { + "External id": 1438139,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684930.006, "dur": 0.501, + "args": { + "External id": 1438140,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684932.040, "dur": 0.651, + "args": { + "External id": 1438141,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684934.777, "dur": 0.611, + "args": { + "External id": 1438142,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853684937.004, "dur": 0.388, + "args": { + "External id": 1438143,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853684958.616, "dur": 65.627, + "args": { + "External id": 1438144,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853685143.544, "dur": 408.307, + "args": { + "External id": 1438145,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853685180.920, "dur": 365.215, + "args": { + "External id": 1438146,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18438, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853685193.459, "dur": 346.288, + "args": { + "External id": 1438147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853685574.964, "dur": 2.775, + "args": { + "External id": 1438148,"Record function id": 0, "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": 18440, "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": 2338706, "tid": 2338706, + "ts": 6413853685683.716, "dur": 30774.963, + "args": { + "External id": 1438149,"Record function id": 0, "Ev Idx": 18441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685803.903, "dur": 7.184, + "args": { + "External id": 1438150,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685815.356, "dur": 1.264, + "args": { + "External id": 1438151,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685818.841, "dur": 4.006, + "args": { + "External id": 1438152,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685824.668, "dur": 0.980, + "args": { + "External id": 1438153,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685827.468, "dur": 1.163, + "args": { + "External id": 1438154,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685829.954, "dur": 0.669, + "args": { + "External id": 1438155,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685832.407, "dur": 1.112, + "args": { + "External id": 1438156,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685835.328, "dur": 2.136, + "args": { + "External id": 1438157,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685838.944, "dur": 0.837, + "args": { + "External id": 1438158,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853685841.403, "dur": 0.886, + "args": { + "External id": 1438159,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853685862.824, "dur": 30531.578, + "args": { + "External id": 1438160,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853685881.383, "dur": 30501.969, + "args": { + "External id": 1438161,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853685900.528, "dur": 19.602, + "args": { + "External id": 1438162,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853685923.944, "dur": 30414.429, + "args": { + "External id": 1438163,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853685926.620, "dur": 30410.809, + "args": { + "External id": 1438164,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853685930.731, "dur": 6.628, + "args": { + "External id": 1438165,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853685939.531, "dur": 30392.589, + "args": { + "External id": 1438166,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853716650.117, "dur": 43.079, + "args": { + "External id": 1438167,"Sequence number": 15348936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18459 + } + }, + { + "ph": "s", "id": 399, "pid": 2338706, "tid": 2338706, "ts": 6413853716650.117, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853716672.841, "dur": 14.331, + "args": { + "External id": 1438168,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853716678.688, "dur": 7.339, + "args": { + "External id": 1438169,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853716777.270, "dur": 84.467, + "args": { + "External id": 1438170,"Record function id": 0, "Ev Idx": 18462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853716863.502, "dur": 1428.856, + "args": { + "External id": 1438171,"Record function id": 0, "Ev Idx": 18463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853716912.671, "dur": 1363.634, + "args": { + "External id": 1438172,"Sequence number": 15348937, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18464 + } + }, + { + "ph": "s", "id": 398, "pid": 2338706, "tid": 2338706, "ts": 6413853716912.671, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853717013.491, "dur": 112.374, + "args": { + "External id": 1438173,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853717156.174, "dur": 116.277, + "args": { + "External id": 1438174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853717291.229, "dur": 44.684, + "args": { + "External id": 1438175,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853717344.375, "dur": 36.927, + "args": { + "External id": 1438176,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853717421.655, "dur": 36.629, + "args": { + "External id": 1438177,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853717482.241, "dur": 21.692, + "args": { + "External id": 1438178,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853717532.011, "dur": 164.085, + "args": { + "External id": 1438179,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853717594.431, "dur": 15.906, + "args": { + "External id": 1438180,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853717602.115, "dur": 7.245, + "args": { + "External id": 1438181,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853717614.967, "dur": 4.764, + "args": { + "External id": 1438182,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853717621.313, "dur": 1.482, + "args": { + "External id": 1438183,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853717625.558, "dur": 6.226, + "args": { + "External id": 1438184,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853717711.259, "dur": 56.027, + "args": { + "External id": 1438185,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853717803.509, "dur": 36.063, + "args": { + "External id": 1438186,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853717853.115, "dur": 54.991, + "args": { + "External id": 1438187,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853717926.680, "dur": 45.176, + "args": { + "External id": 1438188,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853718018.734, "dur": 69.919, + "args": { + "External id": 1438189,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853718101.868, "dur": 52.403, + "args": { + "External id": 1438190,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853718176.546, "dur": 22.140, + "args": { + "External id": 1438191,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18483 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 2338706, "tid": 2338706, + "ts": 6413853718368.031, "dur": 94.916, + "args": { + "External id": 1438192,"Record function id": 0, "Ev Idx": 18484 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338706, "tid": 2338706, + "ts": 6413853718549.154, "dur": 55.664, + "args": { + "External id": 1438193,"Record function id": 0, "Ev Idx": 18485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338706, "tid": 2338706, + "ts": 6413853718616.252, "dur": 34745.201, + "args": { + "External id": 1438194,"Record function id": 0, "Ev Idx": 18486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338706, "tid": 2338706, + "ts": 6413853718628.093, "dur": 1117.934, + "args": { + "External id": 1438195,"Record function id": 0, "Ev Idx": 18487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853718727.289, "dur": 9.952, + "args": { + "External id": 1438196,"Record function id": 0, "Concrete Inputs": ["[27264000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853718753.021, "dur": 38.864, + "args": { + "External id": 1438197,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718759.713, "dur": 2.431, + "args": { + "External id": 1438198,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718765.661, "dur": 0.665, + "args": { + "External id": 1438199,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718768.228, "dur": 0.533, + "args": { + "External id": 1438200,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718770.931, "dur": 0.550, + "args": { + "External id": 1438201,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718772.894, "dur": 0.666, + "args": { + "External id": 1438202,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718775.781, "dur": 0.712, + "args": { + "External id": 1438203,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718778.417, "dur": 2.535, + "args": { + "External id": 1438204,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718782.902, "dur": 0.531, + "args": { + "External id": 1438205,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853718784.958, "dur": 0.495, + "args": { + "External id": 1438206,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853718804.960, "dur": 63.728, + "args": { + "External id": 1438207,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 2338706, "tid": 2338706, + "ts": 6413853718907.630, "dur": 264.679, + "args": { + "External id": 1438208,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [], [], [], [], [], []], "Ev Idx": 18500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853718959.189, "dur": 5.600, + "args": { + "External id": 1438209,"Record function id": 0, "Concrete Inputs": ["[218112000]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 2338706, "tid": 2338706, + "ts": 6413853718971.472, "dur": 37.425, + "args": { + "External id": 1438210,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853718997.385, "dur": 11.022, + "args": { + "External id": 1438211,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "27264000", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[218112000], [], [], [], []], "Ev Idx": 18503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719004.378, "dur": 1.398, + "args": { + "External id": 1438212,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[218112000], [], [], []], "Ev Idx": 18504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 2338706, "tid": 2338706, + "ts": 6413853719019.192, "dur": 74.645, + "args": { + "External id": 1438213,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[27264000], [], []], "Ev Idx": 18505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719030.882, "dur": 0.884, + "args": { + "External id": 1438214,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719033.982, "dur": 0.623, + "args": { + "External id": 1438215,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719036.078, "dur": 0.405, + "args": { + "External id": 1438216,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719038.413, "dur": 2.814, + "args": { + "External id": 1438217,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "2621952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719042.465, "dur": 0.512, + "args": { + "External id": 1438218,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "3146240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719044.923, "dur": 0.607, + "args": { + "External id": 1438219,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "5243392"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719047.083, "dur": 0.454, + "args": { + "External id": 1438220,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "5243904"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719049.284, "dur": 0.636, + "args": { + "External id": 1438221,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "12583936"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853719051.419, "dur": 35.335, + "args": { + "External id": 1438222,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "19923968"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[27264000], [], [], []], "Ev Idx": 18514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853719113.520, "dur": 47.713, + "args": { + "External id": 1438223,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], [[512], [2097152], [524288], [524288], [2097152], [512], [7340032], [7340032], [7340032]], []], "Ev Idx": 18515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 2338706, "tid": 2338706, + "ts": 6413853719242.385, "dur": 400.910, + "args": { + "External id": 1438224,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[218112000], [27264000], [], [], []], "Ev Idx": 18516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853719273.927, "dur": 363.675, + "args": { + "External id": 1438225,"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": 218112000, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[27264000], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 18517, "In msg nelems": 27264000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 2338706, "tid": 2338706, + "ts": 6413853719285.613, "dur": 345.349, + "args": { + "External id": 1438226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[27264000]], "Ev Idx": 18518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413853719666.438, "dur": 2.687, + "args": { + "External id": 1438227,"Record function id": 0, "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": 18519, "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": 2338706, "tid": 2338706, + "ts": 6413853719769.483, "dur": 33341.103, + "args": { + "External id": 1438228,"Record function id": 0, "Ev Idx": 18520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719879.392, "dur": 6.385, + "args": { + "External id": 1438229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[218112000], []], "Ev Idx": 18521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719889.699, "dur": 0.979, + "args": { + "External id": 1438230,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719892.837, "dur": 4.114, + "args": { + "External id": 1438231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719899.024, "dur": 0.834, + "args": { + "External id": 1438232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719901.404, "dur": 0.984, + "args": { + "External id": 1438233,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 18525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719903.991, "dur": 0.873, + "args": { + "External id": 1438234,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[16777216], []], "Ev Idx": 18526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719906.799, "dur": 1.028, + "args": { + "External id": 1438235,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 18527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719910.358, "dur": 2.665, + "args": { + "External id": 1438236,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719914.559, "dur": 0.967, + "args": { + "External id": 1438237,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853719917.457, "dur": 0.651, + "args": { + "External id": 1438238,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[58720256], []], "Ev Idx": 18530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853719937.708, "dur": 33082.849, + "args": { + "External id": 1438239,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853719954.561, "dur": 33054.090, + "args": { + "External id": 1438240,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "Input Dims": [[8, 27264000], [], [], [[8, 512], [8, 2097152], [8, 524288], [8, 524288], [8, 2097152], [8, 512], [8, 7340032], [8, 7340032], [8, 7340032]]], "Ev Idx": 18532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853720025.592, "dur": 21.382, + "args": { + "External id": 1438241,"Record function id": 0, "Concrete Inputs": ["[3845]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853720088.673, "dur": 32861.259, + "args": { + "External id": 1438242,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], [], []], "Ev Idx": 18534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853720092.619, "dur": 32855.919, + "args": { + "External id": 1438243,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[3845], [], [], [], [], [], []], "Ev Idx": 18535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853720098.161, "dur": 8.133, + "args": { + "External id": 1438244,"Record function id": 0, "Concrete Inputs": ["[3845]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853720108.770, "dur": 32835.367, + "args": { + "External id": 1438245,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[3845], [3845], []], "Ev Idx": 18537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853753291.059, "dur": 41.521, + "args": { + "External id": 1438246,"Sequence number": 15348938, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096]], "Ev Idx": 18538 + } + }, + { + "ph": "s", "id": 397, "pid": 2338706, "tid": 2338706, "ts": 6413853753291.059, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853753313.171, "dur": 13.762, + "args": { + "External id": 1438247,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1]], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096]], "Ev Idx": 18539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853753318.973, "dur": 7.645, + "args": { + "External id": 1438248,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853753407.715, "dur": 81.439, + "args": { + "External id": 1438249,"Record function id": 0, "Ev Idx": 18541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338706, "tid": 2338706, + "ts": 6413853753490.746, "dur": 1348.387, + "args": { + "External id": 1438250,"Record function id": 0, "Ev Idx": 18542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853753533.878, "dur": 1288.418, + "args": { + "External id": 1438251,"Sequence number": 15348939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1], [4096, 1], [4096, 1], [4096, 1], [64, 1], [64, 1], [4096, 1], [1], [4096, 1], [4096, 1], [14336, 1]], "Input Dims": [[8, 4096, 4096], [4096], [4096, 4096], [1024, 4096], [1024, 4096], [4096, 64], [4096, 64], [4096, 4096], [4096], [14336, 4096], [14336, 4096], [4096, 14336]], "Ev Idx": 18543 + } + }, + { + "ph": "s", "id": 396, "pid": 2338706, "tid": 2338706, "ts": 6413853753533.878, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853753613.600, "dur": 60.446, + "args": { + "External id": 1438252,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853753690.102, "dur": 119.226, + "args": { + "External id": 1438253,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853753825.580, "dur": 42.312, + "args": { + "External id": 1438254,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853753876.114, "dur": 35.973, + "args": { + "External id": 1438255,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [1024, 1]], "Input Dims": [[32768, 4096], [4096, 1024], [32768, 1024]], "Ev Idx": 18547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853753942.985, "dur": 33.038, + "args": { + "External id": 1438256,"kernel_hash": "cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "32", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/jm/cjmcqz64yvhehczbluucptutsrk7tnydhfpcpgubhbobfvggfk4t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [16777216, 4096, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [8, 4096, 32, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_2", "pid": 2338706, "tid": 2338706, + "ts": 6413853754024.816, "dur": 26.306, + "args": { + "External id": 1438257,"kernel_hash": "c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "8", "4096", "8", "128", "64", "4096", "32", "128", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/73/c73gzh6nuvbz6lmwuwolvfztyyldp6eupvut57avgqbs3cxeovs2.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 18549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853754119.212, "dur": 161.796, + "args": { + "External id": 1438258,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853754178.828, "dur": 17.102, + "args": { + "External id": 1438259,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853754186.242, "dur": 8.533, + "args": { + "External id": 1438260,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853754199.529, "dur": 5.083, + "args": { + "External id": 1438261,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853754206.113, "dur": 1.730, + "args": { + "External id": 1438262,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853754211.106, "dur": 5.891, + "args": { + "External id": 1438263,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853754295.311, "dur": 69.087, + "args": { + "External id": 1438264,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [4096, 1]], "Input Dims": [[32768, 4096], [4096, 4096], [32768, 4096]], "Ev Idx": 18556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_3", "pid": 2338706, "tid": 2338706, + "ts": 6413853754401.405, "dur": 38.028, + "args": { + "External id": 1438265,"kernel_hash": "cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/vu/cvumbknuhbwm7xbr365sswb3nb5beykodkjazo5efrnsnox6hxls.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [4096, 1], [4096, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768, 4096], [4096], [32768, 4096], [32768, 4096], [32768], [], [], [], [], [], [], [], [], []], "Ev Idx": 18557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853754452.064, "dur": 52.189, + "args": { + "External id": 1438266,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853754515.443, "dur": 43.103, + "args": { + "External id": 1438267,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096], [14336, 1]], "Input Dims": [[32768, 4096], [4096, 14336], [32768, 14336]], "Ev Idx": 18559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853754581.563, "dur": 32.393, + "args": { + "External id": 1438268,"kernel_hash": "cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/fg/cfgxszr4z6danmlluxsg5ihv5lmhtc5ofjjkq45okcrthgtnm6sd.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[14336, 1], [14336, 1], [58720256, 14336, 1], []], "Input Dims": [[32768, 14336], [32768, 14336], [8, 4096, 14336], []], "Ev Idx": 18560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853754621.403, "dur": 45.971, + "args": { + "External id": 1438269,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336], [4096, 1]], "Input Dims": [[32768, 14336], [14336, 4096], [32768, 4096]], "Ev Idx": 18561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 2338706, "tid": 2338706, + "ts": 6413853754686.845, "dur": 52.243, + "args": { + "External id": 1438270,"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": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [32768, 4096], []], "Ev Idx": 18562 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 2338706, "tid": 2338706, + "ts": 6413853754934.023, "dur": 75.620, + "args": { + "External id": 1438271,"Record function id": 0, "Ev Idx": 18563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853755239.721, "dur": 671.849, + "args": { + "External id": 1438272,"Sequence number": 15348940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18564 + } + }, + { + "ph": "s", "id": 395, "pid": 2338706, "tid": 2338706, "ts": 6413853755239.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853755296.220, "dur": 12.118, + "args": { + "External id": 1438273,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853755300.020, "dur": 7.805, + "args": { + "External id": 1438274,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853755601.149, "dur": 19.467, + "args": { + "External id": 1438275,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853755606.007, "dur": 13.500, + "args": { + "External id": 1438276,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853755663.729, "dur": 7.323, + "args": { + "External id": 1438277,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853755885.251, "dur": 6.571, + "args": { + "External id": 1438278,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853755886.780, "dur": 4.725, + "args": { + "External id": 1438279,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853755943.758, "dur": 222.740, + "args": { + "External id": 1438280,"Sequence number": 15348941, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853755946.047, "dur": 13.565, + "args": { + "External id": 1438281,"Sequence number": 15348941, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18573 + } + }, + { + "ph": "s", "id": 394, "pid": 2338706, "tid": 2338706, "ts": 6413853755946.047, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853755951.483, "dur": 6.257, + "args": { + "External id": 1438282,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853755954.971, "dur": 2.324, + "args": { + "External id": 1438283,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853755961.815, "dur": 204.177, + "args": { + "External id": 1438284,"Sequence number": 15348942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853755965.063, "dur": 6.929, + "args": { + "External id": 1438285,"Sequence number": 15348942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853755967.656, "dur": 4.149, + "args": { + "External id": 1438286,"Sequence number": 15348942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18578 + } + }, + { + "ph": "s", "id": 393, "pid": 2338706, "tid": 2338706, "ts": 6413853755967.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853755973.456, "dur": 176.630, + "args": { + "External id": 1438287,"Sequence number": 15348943, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18579 + } + }, + { + "ph": "s", "id": 392, "pid": 2338706, "tid": 2338706, "ts": 6413853755973.456, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756156.290, "dur": 8.156, + "args": { + "External id": 1438288,"Sequence number": 15348944, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18580 + } + }, + { + "ph": "s", "id": 391, "pid": 2338706, "tid": 2338706, "ts": 6413853756156.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853756183.045, "dur": 82.225, + "args": { + "External id": 1438289,"Sequence number": 15348945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853756183.997, "dur": 8.417, + "args": { + "External id": 1438290,"Sequence number": 15348945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18582 + } + }, + { + "ph": "s", "id": 390, "pid": 2338706, "tid": 2338706, "ts": 6413853756183.997, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853756186.802, "dur": 4.153, + "args": { + "External id": 1438291,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853756189.168, "dur": 1.552, + "args": { + "External id": 1438292,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853756193.242, "dur": 71.702, + "args": { + "External id": 1438293,"Sequence number": 15348946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853756195.303, "dur": 4.981, + "args": { + "External id": 1438294,"Sequence number": 15348946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756196.774, "dur": 3.349, + "args": { + "External id": 1438295,"Sequence number": 15348946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18587 + } + }, + { + "ph": "s", "id": 389, "pid": 2338706, "tid": 2338706, "ts": 6413853756196.774, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853756200.894, "dur": 58.237, + "args": { + "External id": 1438296,"Sequence number": 15348947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18588 + } + }, + { + "ph": "s", "id": 388, "pid": 2338706, "tid": 2338706, "ts": 6413853756200.894, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756261.155, "dur": 3.253, + "args": { + "External id": 1438297,"Sequence number": 15348948, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18589 + } + }, + { + "ph": "s", "id": 387, "pid": 2338706, "tid": 2338706, "ts": 6413853756261.155, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853756274.146, "dur": 70.473, + "args": { + "External id": 1438298,"Sequence number": 15348949, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853756274.995, "dur": 6.829, + "args": { + "External id": 1438299,"Sequence number": 15348949, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18591 + } + }, + { + "ph": "s", "id": 386, "pid": 2338706, "tid": 2338706, "ts": 6413853756274.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853756277.662, "dur": 2.881, + "args": { + "External id": 1438300,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853756279.445, "dur": 0.936, + "args": { + "External id": 1438301,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853756282.415, "dur": 61.884, + "args": { + "External id": 1438302,"Sequence number": 15348950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853756284.070, "dur": 5.765, + "args": { + "External id": 1438303,"Sequence number": 15348950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756284.970, "dur": 4.699, + "args": { + "External id": 1438304,"Sequence number": 15348950, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18596 + } + }, + { + "ph": "s", "id": 385, "pid": 2338706, "tid": 2338706, "ts": 6413853756284.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853756290.593, "dur": 46.315, + "args": { + "External id": 1438305,"Sequence number": 15348951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18597 + } + }, + { + "ph": "s", "id": 384, "pid": 2338706, "tid": 2338706, "ts": 6413853756290.593, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756338.947, "dur": 4.935, + "args": { + "External id": 1438306,"Sequence number": 15348952, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18598 + } + }, + { + "ph": "s", "id": 383, "pid": 2338706, "tid": 2338706, "ts": 6413853756338.947, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853756368.359, "dur": 4.726, + "args": { + "External id": 1438307,"Sequence number": 15348953, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756369.549, "dur": 3.300, + "args": { + "External id": 1438308,"Sequence number": 15348953, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18600 + } + }, + { + "ph": "s", "id": 382, "pid": 2338706, "tid": 2338706, "ts": 6413853756369.549, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853756381.829, "dur": 7.396, + "args": { + "External id": 1438309,"Sequence number": 15348954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756383.028, "dur": 6.024, + "args": { + "External id": 1438310,"Sequence number": 15348954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18602 + } + }, + { + "ph": "s", "id": 381, "pid": 2338706, "tid": 2338706, "ts": 6413853756383.028, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853756394.353, "dur": 3.882, + "args": { + "External id": 1438311,"Sequence number": 15348955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853756395.476, "dur": 2.605, + "args": { + "External id": 1438312,"Sequence number": 15348955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18604 + } + }, + { + "ph": "s", "id": 380, "pid": 2338706, "tid": 2338706, "ts": 6413853756395.476, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853756444.456, "dur": 212.180, + "args": { + "External id": 1438313,"Sequence number": 15348956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18605 + } + }, + { + "ph": "s", "id": 379, "pid": 2338706, "tid": 2338706, "ts": 6413853756444.456, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853756472.734, "dur": 10.427, + "args": { + "External id": 1438314,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853756476.051, "dur": 6.526, + "args": { + "External id": 1438315,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853756673.952, "dur": 135.646, + "args": { + "External id": 1438316,"Sequence number": 15348957, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18608 + } + }, + { + "ph": "s", "id": 378, "pid": 2338706, "tid": 2338706, "ts": 6413853756673.952, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853756691.916, "dur": 8.063, + "args": { + "External id": 1438317,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853756694.498, "dur": 5.074, + "args": { + "External id": 1438318,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413853756845.961, "dur": 282.172, + "args": { + "External id": 1438319,"Sequence number": 15348958, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18611 + } + }, + { + "ph": "s", "id": 377, "pid": 2338706, "tid": 2338706, "ts": 6413853756845.961, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853756881.257, "dur": 168.574, + "args": { + "External id": 1438320,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853756939.948, "dur": 9.139, + "args": { + "External id": 1438321,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853756943.363, "dur": 5.178, + "args": { + "External id": 1438322,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853756952.422, "dur": 3.920, + "args": { + "External id": 1438323,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853756957.847, "dur": 1.398, + "args": { + "External id": 1438324,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853756962.114, "dur": 4.156, + "args": { + "External id": 1438325,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413853757105.285, "dur": 6.723, + "args": { + "External id": 1438326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757136.292, "dur": 7.851, + "args": { + "External id": 1438327,"Sequence number": 15348959, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757138.319, "dur": 5.621, + "args": { + "External id": 1438328,"Sequence number": 15348959, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18620 + } + }, + { + "ph": "s", "id": 376, "pid": 2338706, "tid": 2338706, "ts": 6413853757138.319, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853757161.162, "dur": 138.621, + "args": { + "External id": 1438329,"Sequence number": 15348960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853757162.451, "dur": 9.994, + "args": { + "External id": 1438330,"Sequence number": 15348960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18622 + } + }, + { + "ph": "s", "id": 375, "pid": 2338706, "tid": 2338706, "ts": 6413853757162.451, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853757165.391, "dur": 5.633, + "args": { + "External id": 1438331,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853757168.629, "dur": 2.058, + "args": { + "External id": 1438332,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853757173.996, "dur": 125.393, + "args": { + "External id": 1438333,"Sequence number": 15348961, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757176.422, "dur": 4.254, + "args": { + "External id": 1438334,"Sequence number": 15348961, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757177.108, "dur": 3.378, + "args": { + "External id": 1438335,"Sequence number": 15348961, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18627 + } + }, + { + "ph": "s", "id": 374, "pid": 2338706, "tid": 2338706, "ts": 6413853757177.108, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853757181.917, "dur": 109.673, + "args": { + "External id": 1438336,"Sequence number": 15348962, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18628 + } + }, + { + "ph": "s", "id": 373, "pid": 2338706, "tid": 2338706, "ts": 6413853757181.917, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757294.610, "dur": 3.842, + "args": { + "External id": 1438337,"Sequence number": 15348963, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18629 + } + }, + { + "ph": "s", "id": 372, "pid": 2338706, "tid": 2338706, "ts": 6413853757294.610, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853757344.731, "dur": 278.449, + "args": { + "External id": 1438338,"Sequence number": 15348964, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18630 + } + }, + { + "ph": "s", "id": 371, "pid": 2338706, "tid": 2338706, "ts": 6413853757344.731, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757376.151, "dur": 3.511, + "args": { + "External id": 1438339,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757377.383, "dur": 1.968, + "args": { + "External id": 1438340,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853757384.720, "dur": 9.589, + "args": { + "External id": 1438341,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757386.228, "dur": 7.958, + "args": { + "External id": 1438342,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757389.691, "dur": 4.358, + "args": { + "External id": 1438343,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853757403.851, "dur": 10.588, + "args": { + "External id": 1438344,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853757407.365, "dur": 6.600, + "args": { + "External id": 1438345,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853757422.193, "dur": 3.613, + "args": { + "External id": 1438346,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853757430.214, "dur": 3.635, + "args": { + "External id": 1438347,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757598.333, "dur": 3.594, + "args": { + "External id": 1438348,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757599.582, "dur": 2.047, + "args": { + "External id": 1438349,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757607.649, "dur": 2.337, + "args": { + "External id": 1438350,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757608.748, "dur": 1.132, + "args": { + "External id": 1438351,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853757646.380, "dur": 115.595, + "args": { + "External id": 1438352,"Sequence number": 15348965, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853757647.530, "dur": 8.271, + "args": { + "External id": 1438353,"Sequence number": 15348965, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18645 + } + }, + { + "ph": "s", "id": 370, "pid": 2338706, "tid": 2338706, "ts": 6413853757647.530, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853757650.043, "dur": 4.432, + "args": { + "External id": 1438354,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853757652.504, "dur": 1.634, + "args": { + "External id": 1438355,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853757656.627, "dur": 105.041, + "args": { + "External id": 1438356,"Sequence number": 15348966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757661.031, "dur": 4.828, + "args": { + "External id": 1438357,"Sequence number": 15348966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757662.214, "dur": 3.472, + "args": { + "External id": 1438358,"Sequence number": 15348966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18650 + } + }, + { + "ph": "s", "id": 369, "pid": 2338706, "tid": 2338706, "ts": 6413853757662.214, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853757666.748, "dur": 85.093, + "args": { + "External id": 1438359,"Sequence number": 15348967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18651 + } + }, + { + "ph": "s", "id": 368, "pid": 2338706, "tid": 2338706, "ts": 6413853757666.748, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757754.972, "dur": 5.859, + "args": { + "External id": 1438360,"Sequence number": 15348968, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18652 + } + }, + { + "ph": "s", "id": 367, "pid": 2338706, "tid": 2338706, "ts": 6413853757754.972, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853757773.515, "dur": 80.987, + "args": { + "External id": 1438361,"Sequence number": 15348969, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853757774.591, "dur": 7.193, + "args": { + "External id": 1438362,"Sequence number": 15348969, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18654 + } + }, + { + "ph": "s", "id": 366, "pid": 2338706, "tid": 2338706, "ts": 6413853757774.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853757777.076, "dur": 3.323, + "args": { + "External id": 1438363,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853757779.095, "dur": 1.127, + "args": { + "External id": 1438364,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853757782.558, "dur": 71.639, + "args": { + "External id": 1438365,"Sequence number": 15348970, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757784.282, "dur": 6.347, + "args": { + "External id": 1438366,"Sequence number": 15348970, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757785.342, "dur": 5.098, + "args": { + "External id": 1438367,"Sequence number": 15348970, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18659 + } + }, + { + "ph": "s", "id": 365, "pid": 2338706, "tid": 2338706, "ts": 6413853757785.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853757791.187, "dur": 57.403, + "args": { + "External id": 1438368,"Sequence number": 15348971, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18660 + } + }, + { + "ph": "s", "id": 364, "pid": 2338706, "tid": 2338706, "ts": 6413853757791.187, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853757850.550, "dur": 3.190, + "args": { + "External id": 1438369,"Sequence number": 15348972, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18661 + } + }, + { + "ph": "s", "id": 363, "pid": 2338706, "tid": 2338706, "ts": 6413853757850.550, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853757878.200, "dur": 254.731, + "args": { + "External id": 1438370,"Sequence number": 15348973, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18662 + } + }, + { + "ph": "s", "id": 362, "pid": 2338706, "tid": 2338706, "ts": 6413853757878.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853757923.855, "dur": 5.572, + "args": { + "External id": 1438371,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853757967.309, "dur": 146.098, + "args": { + "External id": 1438372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853757968.292, "dur": 5.497, + "args": { + "External id": 1438373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853757969.868, "dur": 2.978, + "args": { + "External id": 1438374,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853757971.896, "dur": 0.773, + "args": { + "External id": 1438375,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853757974.943, "dur": 138.098, + "args": { + "External id": 1438376,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853757998.990, "dur": 5.042, + "args": { + "External id": 1438377,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758001.501, "dur": 2.222, + "args": { + "External id": 1438378,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853758004.730, "dur": 101.488, + "args": { + "External id": 1438379,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 18671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758110.158, "dur": 1.986, + "args": { + "External id": 1438380,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413853758145.660, "dur": 34.762, + "args": { + "External id": 1438381,"Sequence number": 15348974, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 18673 + } + }, + { + "ph": "s", "id": 361, "pid": 2338706, "tid": 2338706, "ts": 6413853758145.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853758225.952, "dur": 222.050, + "args": { + "External id": 1438382,"Sequence number": 15348975, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18674 + } + }, + { + "ph": "s", "id": 360, "pid": 2338706, "tid": 2338706, "ts": 6413853758225.952, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758251.233, "dur": 3.764, + "args": { + "External id": 1438383,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758252.539, "dur": 2.251, + "args": { + "External id": 1438384,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853758264.462, "dur": 8.797, + "args": { + "External id": 1438385,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853758267.655, "dur": 5.207, + "args": { + "External id": 1438386,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853758280.159, "dur": 4.931, + "args": { + "External id": 1438387,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758431.260, "dur": 3.710, + "args": { + "External id": 1438388,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758432.461, "dur": 2.085, + "args": { + "External id": 1438389,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853758470.782, "dur": 107.933, + "args": { + "External id": 1438390,"Sequence number": 15348976, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853758471.763, "dur": 9.072, + "args": { + "External id": 1438391,"Sequence number": 15348976, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18683 + } + }, + { + "ph": "s", "id": 359, "pid": 2338706, "tid": 2338706, "ts": 6413853758471.763, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853758474.608, "dur": 4.945, + "args": { + "External id": 1438392,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853758477.473, "dur": 1.830, + "args": { + "External id": 1438393,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853758482.516, "dur": 95.857, + "args": { + "External id": 1438394,"Sequence number": 15348977, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758484.548, "dur": 7.497, + "args": { + "External id": 1438395,"Sequence number": 15348977, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758485.790, "dur": 6.068, + "args": { + "External id": 1438396,"Sequence number": 15348977, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18688 + } + }, + { + "ph": "s", "id": 358, "pid": 2338706, "tid": 2338706, "ts": 6413853758485.790, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853758492.968, "dur": 74.882, + "args": { + "External id": 1438397,"Sequence number": 15348978, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18689 + } + }, + { + "ph": "s", "id": 357, "pid": 2338706, "tid": 2338706, "ts": 6413853758492.968, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758570.669, "dur": 6.934, + "args": { + "External id": 1438398,"Sequence number": 15348979, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18690 + } + }, + { + "ph": "s", "id": 356, "pid": 2338706, "tid": 2338706, "ts": 6413853758570.669, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853758588.149, "dur": 73.998, + "args": { + "External id": 1438399,"Sequence number": 15348980, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853758589.004, "dur": 9.368, + "args": { + "External id": 1438400,"Sequence number": 15348980, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18692 + } + }, + { + "ph": "s", "id": 355, "pid": 2338706, "tid": 2338706, "ts": 6413853758589.004, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853758594.454, "dur": 2.871, + "args": { + "External id": 1438401,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853758596.070, "dur": 1.057, + "args": { + "External id": 1438402,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853758599.027, "dur": 62.831, + "args": { + "External id": 1438403,"Sequence number": 15348981, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758600.303, "dur": 6.653, + "args": { + "External id": 1438404,"Sequence number": 15348981, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758603.849, "dur": 2.904, + "args": { + "External id": 1438405,"Sequence number": 15348981, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18697 + } + }, + { + "ph": "s", "id": 354, "pid": 2338706, "tid": 2338706, "ts": 6413853758603.849, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853758607.553, "dur": 47.306, + "args": { + "External id": 1438406,"Sequence number": 15348982, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18698 + } + }, + { + "ph": "s", "id": 353, "pid": 2338706, "tid": 2338706, "ts": 6413853758607.553, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758656.832, "dur": 4.073, + "args": { + "External id": 1438407,"Sequence number": 15348983, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18699 + } + }, + { + "ph": "s", "id": 352, "pid": 2338706, "tid": 2338706, "ts": 6413853758656.832, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853758671.556, "dur": 65.525, + "args": { + "External id": 1438408,"Sequence number": 15348984, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853758672.209, "dur": 7.478, + "args": { + "External id": 1438409,"Sequence number": 15348984, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18701 + } + }, + { + "ph": "s", "id": 351, "pid": 2338706, "tid": 2338706, "ts": 6413853758672.209, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853758674.988, "dur": 3.495, + "args": { + "External id": 1438410,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853758677.287, "dur": 1.054, + "args": { + "External id": 1438411,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853758680.557, "dur": 56.106, + "args": { + "External id": 1438412,"Sequence number": 15348985, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758681.595, "dur": 7.767, + "args": { + "External id": 1438413,"Sequence number": 15348985, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758682.358, "dur": 6.818, + "args": { + "External id": 1438414,"Sequence number": 15348985, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18706 + } + }, + { + "ph": "s", "id": 350, "pid": 2338706, "tid": 2338706, "ts": 6413853758682.358, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853758690.148, "dur": 41.058, + "args": { + "External id": 1438415,"Sequence number": 15348986, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18707 + } + }, + { + "ph": "s", "id": 349, "pid": 2338706, "tid": 2338706, "ts": 6413853758690.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758733.837, "dur": 2.356, + "args": { + "External id": 1438416,"Sequence number": 15348987, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18708 + } + }, + { + "ph": "s", "id": 348, "pid": 2338706, "tid": 2338706, "ts": 6413853758733.837, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758754.582, "dur": 5.563, + "args": { + "External id": 1438417,"Sequence number": 15348988, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758756.023, "dur": 3.975, + "args": { + "External id": 1438418,"Sequence number": 15348988, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18710 + } + }, + { + "ph": "s", "id": 347, "pid": 2338706, "tid": 2338706, "ts": 6413853758756.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758768.024, "dur": 4.195, + "args": { + "External id": 1438419,"Sequence number": 15348989, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758769.222, "dur": 2.840, + "args": { + "External id": 1438420,"Sequence number": 15348989, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18712 + } + }, + { + "ph": "s", "id": 346, "pid": 2338706, "tid": 2338706, "ts": 6413853758769.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853758777.143, "dur": 4.587, + "args": { + "External id": 1438421,"Sequence number": 15348990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853758778.587, "dur": 2.982, + "args": { + "External id": 1438422,"Sequence number": 15348990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18714 + } + }, + { + "ph": "s", "id": 345, "pid": 2338706, "tid": 2338706, "ts": 6413853758778.587, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853758814.182, "dur": 234.211, + "args": { + "External id": 1438423,"Sequence number": 15348991, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18715 + } + }, + { + "ph": "s", "id": 344, "pid": 2338706, "tid": 2338706, "ts": 6413853758814.182, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853758836.911, "dur": 39.498, + "args": { + "External id": 1438424,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853758865.718, "dur": 10.289, + "args": { + "External id": 1438425,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853759116.847, "dur": 182.326, + "args": { + "External id": 1438426,"Sequence number": 15348992, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18718 + } + }, + { + "ph": "s", "id": 343, "pid": 2338706, "tid": 2338706, "ts": 6413853759116.847, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853759141.287, "dur": 16.992, + "args": { + "External id": 1438427,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853759145.880, "dur": 11.152, + "args": { + "External id": 1438428,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413853759339.270, "dur": 207.434, + "args": { + "External id": 1438429,"Sequence number": 15348993, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18721 + } + }, + { + "ph": "s", "id": 342, "pid": 2338706, "tid": 2338706, "ts": 6413853759339.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853759373.389, "dur": 142.133, + "args": { + "External id": 1438430,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853759426.964, "dur": 9.884, + "args": { + "External id": 1438431,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853759431.088, "dur": 5.244, + "args": { + "External id": 1438432,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853759440.499, "dur": 5.183, + "args": { + "External id": 1438433,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853759447.810, "dur": 1.546, + "args": { + "External id": 1438434,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853759452.100, "dur": 5.044, + "args": { + "External id": 1438435,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413853759528.679, "dur": 6.145, + "args": { + "External id": 1438436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853759553.219, "dur": 8.628, + "args": { + "External id": 1438437,"Sequence number": 15348994, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759555.271, "dur": 6.297, + "args": { + "External id": 1438438,"Sequence number": 15348994, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18730 + } + }, + { + "ph": "s", "id": 341, "pid": 2338706, "tid": 2338706, "ts": 6413853759555.271, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853759576.635, "dur": 135.016, + "args": { + "External id": 1438439,"Sequence number": 15348995, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853759577.722, "dur": 10.442, + "args": { + "External id": 1438440,"Sequence number": 15348995, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18732 + } + }, + { + "ph": "s", "id": 340, "pid": 2338706, "tid": 2338706, "ts": 6413853759577.722, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853759581.419, "dur": 5.477, + "args": { + "External id": 1438441,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853759584.638, "dur": 1.957, + "args": { + "External id": 1438442,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853759589.663, "dur": 121.491, + "args": { + "External id": 1438443,"Sequence number": 15348996, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853759591.931, "dur": 4.156, + "args": { + "External id": 1438444,"Sequence number": 15348996, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759592.839, "dur": 3.009, + "args": { + "External id": 1438445,"Sequence number": 15348996, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18737 + } + }, + { + "ph": "s", "id": 339, "pid": 2338706, "tid": 2338706, "ts": 6413853759592.839, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853759597.678, "dur": 103.351, + "args": { + "External id": 1438446,"Sequence number": 15348997, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18738 + } + }, + { + "ph": "s", "id": 338, "pid": 2338706, "tid": 2338706, "ts": 6413853759597.678, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759704.125, "dur": 6.196, + "args": { + "External id": 1438447,"Sequence number": 15348998, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18739 + } + }, + { + "ph": "s", "id": 337, "pid": 2338706, "tid": 2338706, "ts": 6413853759704.125, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853759751.922, "dur": 258.573, + "args": { + "External id": 1438448,"Sequence number": 15348999, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18740 + } + }, + { + "ph": "s", "id": 336, "pid": 2338706, "tid": 2338706, "ts": 6413853759751.922, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853759772.297, "dur": 3.359, + "args": { + "External id": 1438449,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759773.486, "dur": 1.927, + "args": { + "External id": 1438450,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853759779.682, "dur": 4.067, + "args": { + "External id": 1438451,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853759780.933, "dur": 2.693, + "args": { + "External id": 1438452,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759782.545, "dur": 0.964, + "args": { + "External id": 1438453,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853759792.605, "dur": 8.460, + "args": { + "External id": 1438454,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853759795.245, "dur": 5.380, + "args": { + "External id": 1438455,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853759808.200, "dur": 3.648, + "args": { + "External id": 1438456,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853759816.167, "dur": 4.253, + "args": { + "External id": 1438457,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853759964.948, "dur": 3.346, + "args": { + "External id": 1438458,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759966.062, "dur": 2.009, + "args": { + "External id": 1438459,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853759972.161, "dur": 2.148, + "args": { + "External id": 1438460,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853759973.203, "dur": 0.997, + "args": { + "External id": 1438461,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853760032.540, "dur": 176.283, + "args": { + "External id": 1438462,"Sequence number": 15349000, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853760033.961, "dur": 10.746, + "args": { + "External id": 1438463,"Sequence number": 15349000, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18755 + } + }, + { + "ph": "s", "id": 335, "pid": 2338706, "tid": 2338706, "ts": 6413853760033.961, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853760037.472, "dur": 5.514, + "args": { + "External id": 1438464,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853760040.798, "dur": 1.957, + "args": { + "External id": 1438465,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853760047.175, "dur": 161.222, + "args": { + "External id": 1438466,"Sequence number": 15349001, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760049.289, "dur": 46.652, + "args": { + "External id": 1438467,"Sequence number": 15349001, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760050.406, "dur": 44.868, + "args": { + "External id": 1438468,"Sequence number": 15349001, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18760 + } + }, + { + "ph": "s", "id": 334, "pid": 2338706, "tid": 2338706, "ts": 6413853760050.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853760097.673, "dur": 99.562, + "args": { + "External id": 1438469,"Sequence number": 15349002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18761 + } + }, + { + "ph": "s", "id": 333, "pid": 2338706, "tid": 2338706, "ts": 6413853760097.673, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760200.453, "dur": 6.970, + "args": { + "External id": 1438470,"Sequence number": 15349003, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18762 + } + }, + { + "ph": "s", "id": 332, "pid": 2338706, "tid": 2338706, "ts": 6413853760200.453, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853760222.021, "dur": 78.012, + "args": { + "External id": 1438471,"Sequence number": 15349004, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853760222.902, "dur": 8.203, + "args": { + "External id": 1438472,"Sequence number": 15349004, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18764 + } + }, + { + "ph": "s", "id": 331, "pid": 2338706, "tid": 2338706, "ts": 6413853760222.902, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853760225.527, "dur": 3.863, + "args": { + "External id": 1438473,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853760228.181, "dur": 0.993, + "args": { + "External id": 1438474,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853760231.962, "dur": 67.798, + "args": { + "External id": 1438475,"Sequence number": 15349005, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760234.324, "dur": 6.271, + "args": { + "External id": 1438476,"Sequence number": 15349005, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760235.534, "dur": 4.882, + "args": { + "External id": 1438477,"Sequence number": 15349005, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18769 + } + }, + { + "ph": "s", "id": 330, "pid": 2338706, "tid": 2338706, "ts": 6413853760235.534, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853760241.441, "dur": 53.336, + "args": { + "External id": 1438478,"Sequence number": 15349006, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18770 + } + }, + { + "ph": "s", "id": 329, "pid": 2338706, "tid": 2338706, "ts": 6413853760241.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760297.059, "dur": 2.265, + "args": { + "External id": 1438479,"Sequence number": 15349007, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18771 + } + }, + { + "ph": "s", "id": 328, "pid": 2338706, "tid": 2338706, "ts": 6413853760297.059, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853760325.075, "dur": 175.497, + "args": { + "External id": 1438480,"Sequence number": 15349008, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18772 + } + }, + { + "ph": "s", "id": 327, "pid": 2338706, "tid": 2338706, "ts": 6413853760325.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853760369.037, "dur": 6.183, + "args": { + "External id": 1438481,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853760416.069, "dur": 69.531, + "args": { + "External id": 1438482,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853760417.464, "dur": 6.096, + "args": { + "External id": 1438483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853760419.475, "dur": 3.045, + "args": { + "External id": 1438484,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853760421.377, "dur": 0.958, + "args": { + "External id": 1438485,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853760424.438, "dur": 60.816, + "args": { + "External id": 1438486,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760425.995, "dur": 3.514, + "args": { + "External id": 1438487,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760427.960, "dur": 1.319, + "args": { + "External id": 1438488,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853760430.132, "dur": 50.514, + "args": { + "External id": 1438489,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 18781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760483.206, "dur": 1.285, + "args": { + "External id": 1438490,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413853760510.470, "dur": 31.984, + "args": { + "External id": 1438491,"Sequence number": 15349009, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 18783 + } + }, + { + "ph": "s", "id": 326, "pid": 2338706, "tid": 2338706, "ts": 6413853760510.470, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853760583.533, "dur": 223.374, + "args": { + "External id": 1438492,"Sequence number": 15349010, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18784 + } + }, + { + "ph": "s", "id": 325, "pid": 2338706, "tid": 2338706, "ts": 6413853760583.533, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760606.160, "dur": 4.093, + "args": { + "External id": 1438493,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760607.489, "dur": 2.513, + "args": { + "External id": 1438494,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853760620.285, "dur": 8.896, + "args": { + "External id": 1438495,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853760623.742, "dur": 5.012, + "args": { + "External id": 1438496,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853760636.421, "dur": 6.225, + "args": { + "External id": 1438497,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760791.081, "dur": 3.624, + "args": { + "External id": 1438498,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760792.552, "dur": 1.937, + "args": { + "External id": 1438499,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853760827.809, "dur": 94.426, + "args": { + "External id": 1438500,"Sequence number": 15349011, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853760828.855, "dur": 7.090, + "args": { + "External id": 1438501,"Sequence number": 15349011, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18793 + } + }, + { + "ph": "s", "id": 324, "pid": 2338706, "tid": 2338706, "ts": 6413853760828.855, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853760830.772, "dur": 3.844, + "args": { + "External id": 1438502,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853760833.152, "dur": 1.236, + "args": { + "External id": 1438503,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853760837.173, "dur": 84.754, + "args": { + "External id": 1438504,"Sequence number": 15349012, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760839.013, "dur": 4.497, + "args": { + "External id": 1438505,"Sequence number": 15349012, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760840.255, "dur": 3.058, + "args": { + "External id": 1438506,"Sequence number": 15349012, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18798 + } + }, + { + "ph": "s", "id": 323, "pid": 2338706, "tid": 2338706, "ts": 6413853760840.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853760844.136, "dur": 70.485, + "args": { + "External id": 1438507,"Sequence number": 15349013, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18799 + } + }, + { + "ph": "s", "id": 322, "pid": 2338706, "tid": 2338706, "ts": 6413853760844.136, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760917.398, "dur": 3.818, + "args": { + "External id": 1438508,"Sequence number": 15349014, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18800 + } + }, + { + "ph": "s", "id": 321, "pid": 2338706, "tid": 2338706, "ts": 6413853760917.398, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853760937.641, "dur": 99.589, + "args": { + "External id": 1438509,"Sequence number": 15349015, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853760938.523, "dur": 6.155, + "args": { + "External id": 1438510,"Sequence number": 15349015, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18802 + } + }, + { + "ph": "s", "id": 320, "pid": 2338706, "tid": 2338706, "ts": 6413853760938.523, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853760940.798, "dur": 2.672, + "args": { + "External id": 1438511,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853760942.199, "dur": 1.042, + "args": { + "External id": 1438512,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853760945.190, "dur": 91.736, + "args": { + "External id": 1438513,"Sequence number": 15349016, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853760946.790, "dur": 7.013, + "args": { + "External id": 1438514,"Sequence number": 15349016, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853760949.916, "dur": 3.708, + "args": { + "External id": 1438515,"Sequence number": 15349016, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18807 + } + }, + { + "ph": "s", "id": 319, "pid": 2338706, "tid": 2338706, "ts": 6413853760949.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853760954.626, "dur": 72.732, + "args": { + "External id": 1438516,"Sequence number": 15349017, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18808 + } + }, + { + "ph": "s", "id": 318, "pid": 2338706, "tid": 2338706, "ts": 6413853760954.626, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761030.650, "dur": 5.564, + "args": { + "External id": 1438517,"Sequence number": 15349018, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18809 + } + }, + { + "ph": "s", "id": 317, "pid": 2338706, "tid": 2338706, "ts": 6413853761030.650, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853761048.324, "dur": 134.437, + "args": { + "External id": 1438518,"Sequence number": 15349019, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853761049.297, "dur": 45.343, + "args": { + "External id": 1438519,"Sequence number": 15349019, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18811 + } + }, + { + "ph": "s", "id": 316, "pid": 2338706, "tid": 2338706, "ts": 6413853761049.297, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853761051.333, "dur": 3.560, + "args": { + "External id": 1438520,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853761053.626, "dur": 1.123, + "args": { + "External id": 1438521,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853761097.792, "dur": 84.710, + "args": { + "External id": 1438522,"Sequence number": 15349020, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853761099.808, "dur": 6.444, + "args": { + "External id": 1438523,"Sequence number": 15349020, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761100.791, "dur": 5.218, + "args": { + "External id": 1438524,"Sequence number": 15349020, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18816 + } + }, + { + "ph": "s", "id": 315, "pid": 2338706, "tid": 2338706, "ts": 6413853761100.791, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853761106.822, "dur": 68.846, + "args": { + "External id": 1438525,"Sequence number": 15349021, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18817 + } + }, + { + "ph": "s", "id": 314, "pid": 2338706, "tid": 2338706, "ts": 6413853761106.822, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761179.018, "dur": 2.833, + "args": { + "External id": 1438526,"Sequence number": 15349022, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18818 + } + }, + { + "ph": "s", "id": 313, "pid": 2338706, "tid": 2338706, "ts": 6413853761179.018, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853761203.517, "dur": 4.314, + "args": { + "External id": 1438527,"Sequence number": 15349023, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761204.582, "dur": 3.060, + "args": { + "External id": 1438528,"Sequence number": 15349023, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18820 + } + }, + { + "ph": "s", "id": 312, "pid": 2338706, "tid": 2338706, "ts": 6413853761204.582, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853761216.259, "dur": 4.014, + "args": { + "External id": 1438529,"Sequence number": 15349024, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761217.516, "dur": 2.601, + "args": { + "External id": 1438530,"Sequence number": 15349024, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18822 + } + }, + { + "ph": "s", "id": 311, "pid": 2338706, "tid": 2338706, "ts": 6413853761217.516, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853761225.578, "dur": 6.329, + "args": { + "External id": 1438531,"Sequence number": 15349025, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761226.779, "dur": 4.967, + "args": { + "External id": 1438532,"Sequence number": 15349025, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18824 + } + }, + { + "ph": "s", "id": 310, "pid": 2338706, "tid": 2338706, "ts": 6413853761226.779, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853761266.965, "dur": 190.290, + "args": { + "External id": 1438533,"Sequence number": 15349026, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18825 + } + }, + { + "ph": "s", "id": 309, "pid": 2338706, "tid": 2338706, "ts": 6413853761266.965, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853761290.097, "dur": 10.744, + "args": { + "External id": 1438534,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853761293.460, "dur": 6.906, + "args": { + "External id": 1438535,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853761473.423, "dur": 125.444, + "args": { + "External id": 1438536,"Sequence number": 15349027, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18828 + } + }, + { + "ph": "s", "id": 308, "pid": 2338706, "tid": 2338706, "ts": 6413853761473.423, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853761489.176, "dur": 8.962, + "args": { + "External id": 1438537,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853761492.278, "dur": 5.437, + "args": { + "External id": 1438538,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413853761630.096, "dur": 205.406, + "args": { + "External id": 1438539,"Sequence number": 15349028, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18831 + } + }, + { + "ph": "s", "id": 307, "pid": 2338706, "tid": 2338706, "ts": 6413853761630.096, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853761662.964, "dur": 143.539, + "args": { + "External id": 1438540,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853761716.578, "dur": 8.270, + "args": { + "External id": 1438541,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853761719.643, "dur": 4.735, + "args": { + "External id": 1438542,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853761728.781, "dur": 7.029, + "args": { + "External id": 1438543,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853761737.317, "dur": 1.197, + "args": { + "External id": 1438544,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853761741.517, "dur": 4.851, + "args": { + "External id": 1438545,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413853761819.304, "dur": 5.274, + "args": { + "External id": 1438546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853761841.358, "dur": 6.533, + "args": { + "External id": 1438547,"Sequence number": 15349029, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761842.971, "dur": 4.740, + "args": { + "External id": 1438548,"Sequence number": 15349029, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18840 + } + }, + { + "ph": "s", "id": 306, "pid": 2338706, "tid": 2338706, "ts": 6413853761842.971, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853761861.393, "dur": 113.582, + "args": { + "External id": 1438549,"Sequence number": 15349030, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853761862.384, "dur": 12.243, + "args": { + "External id": 1438550,"Sequence number": 15349030, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18842 + } + }, + { + "ph": "s", "id": 305, "pid": 2338706, "tid": 2338706, "ts": 6413853761862.384, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853761868.013, "dur": 5.447, + "args": { + "External id": 1438551,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853761871.370, "dur": 1.786, + "args": { + "External id": 1438552,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853761875.925, "dur": 98.787, + "args": { + "External id": 1438553,"Sequence number": 15349031, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853761877.539, "dur": 4.372, + "args": { + "External id": 1438554,"Sequence number": 15349031, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761878.416, "dur": 3.295, + "args": { + "External id": 1438555,"Sequence number": 15349031, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18847 + } + }, + { + "ph": "s", "id": 304, "pid": 2338706, "tid": 2338706, "ts": 6413853761878.416, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853761883.162, "dur": 82.869, + "args": { + "External id": 1438556,"Sequence number": 15349032, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18848 + } + }, + { + "ph": "s", "id": 303, "pid": 2338706, "tid": 2338706, "ts": 6413853761883.162, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853761969.079, "dur": 4.808, + "args": { + "External id": 1438557,"Sequence number": 15349033, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18849 + } + }, + { + "ph": "s", "id": 302, "pid": 2338706, "tid": 2338706, "ts": 6413853761969.079, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853762035.223, "dur": 299.559, + "args": { + "External id": 1438558,"Sequence number": 15349034, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18850 + } + }, + { + "ph": "s", "id": 301, "pid": 2338706, "tid": 2338706, "ts": 6413853762035.223, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762093.504, "dur": 6.046, + "args": { + "External id": 1438559,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762096.263, "dur": 2.966, + "args": { + "External id": 1438560,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853762105.127, "dur": 13.102, + "args": { + "External id": 1438561,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762113.737, "dur": 4.363, + "args": { + "External id": 1438562,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762116.897, "dur": 1.096, + "args": { + "External id": 1438563,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853762127.402, "dur": 12.448, + "args": { + "External id": 1438564,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853762129.816, "dur": 9.646, + "args": { + "External id": 1438565,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853762148.019, "dur": 3.202, + "args": { + "External id": 1438566,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853762155.749, "dur": 3.122, + "args": { + "External id": 1438567,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762311.525, "dur": 3.642, + "args": { + "External id": 1438568,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762312.818, "dur": 2.077, + "args": { + "External id": 1438569,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762317.909, "dur": 2.280, + "args": { + "External id": 1438570,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762318.959, "dur": 1.120, + "args": { + "External id": 1438571,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853762355.495, "dur": 114.819, + "args": { + "External id": 1438572,"Sequence number": 15349035, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853762356.552, "dur": 10.994, + "args": { + "External id": 1438573,"Sequence number": 15349035, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18865 + } + }, + { + "ph": "s", "id": 300, "pid": 2338706, "tid": 2338706, "ts": 6413853762356.552, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853762359.695, "dur": 6.453, + "args": { + "External id": 1438574,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853762364.024, "dur": 1.867, + "args": { + "External id": 1438575,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853762368.497, "dur": 101.451, + "args": { + "External id": 1438576,"Sequence number": 15349036, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762370.517, "dur": 4.584, + "args": { + "External id": 1438577,"Sequence number": 15349036, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762371.350, "dur": 3.617, + "args": { + "External id": 1438578,"Sequence number": 15349036, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18870 + } + }, + { + "ph": "s", "id": 299, "pid": 2338706, "tid": 2338706, "ts": 6413853762371.350, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853762375.972, "dur": 86.203, + "args": { + "External id": 1438579,"Sequence number": 15349037, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18871 + } + }, + { + "ph": "s", "id": 298, "pid": 2338706, "tid": 2338706, "ts": 6413853762375.972, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762464.629, "dur": 4.346, + "args": { + "External id": 1438580,"Sequence number": 15349038, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18872 + } + }, + { + "ph": "s", "id": 297, "pid": 2338706, "tid": 2338706, "ts": 6413853762464.629, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853762479.373, "dur": 78.629, + "args": { + "External id": 1438581,"Sequence number": 15349039, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853762480.244, "dur": 8.750, + "args": { + "External id": 1438582,"Sequence number": 15349039, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18874 + } + }, + { + "ph": "s", "id": 296, "pid": 2338706, "tid": 2338706, "ts": 6413853762480.244, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853762482.130, "dur": 5.702, + "args": { + "External id": 1438583,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853762484.090, "dur": 3.547, + "args": { + "External id": 1438584,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853762489.675, "dur": 68.017, + "args": { + "External id": 1438585,"Sequence number": 15349040, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762490.956, "dur": 6.518, + "args": { + "External id": 1438586,"Sequence number": 15349040, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762492.173, "dur": 5.104, + "args": { + "External id": 1438587,"Sequence number": 15349040, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18879 + } + }, + { + "ph": "s", "id": 295, "pid": 2338706, "tid": 2338706, "ts": 6413853762492.173, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853762498.400, "dur": 52.520, + "args": { + "External id": 1438588,"Sequence number": 15349041, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18880 + } + }, + { + "ph": "s", "id": 294, "pid": 2338706, "tid": 2338706, "ts": 6413853762498.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762553.293, "dur": 3.759, + "args": { + "External id": 1438589,"Sequence number": 15349042, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18881 + } + }, + { + "ph": "s", "id": 293, "pid": 2338706, "tid": 2338706, "ts": 6413853762553.293, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853762580.366, "dur": 166.378, + "args": { + "External id": 1438590,"Sequence number": 15349043, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18882 + } + }, + { + "ph": "s", "id": 292, "pid": 2338706, "tid": 2338706, "ts": 6413853762580.366, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853762622.346, "dur": 5.445, + "args": { + "External id": 1438591,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853762664.222, "dur": 70.072, + "args": { + "External id": 1438592,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853762665.147, "dur": 5.299, + "args": { + "External id": 1438593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853762666.859, "dur": 2.467, + "args": { + "External id": 1438594,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853762668.381, "dur": 0.753, + "args": { + "External id": 1438595,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853762671.553, "dur": 62.325, + "args": { + "External id": 1438596,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762673.253, "dur": 4.759, + "args": { + "External id": 1438597,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762676.530, "dur": 1.358, + "args": { + "External id": 1438598,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853762678.557, "dur": 48.570, + "args": { + "External id": 1438599,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 18891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762729.926, "dur": 3.282, + "args": { + "External id": 1438600,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413853762756.092, "dur": 29.561, + "args": { + "External id": 1438601,"Sequence number": 15349044, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 18893 + } + }, + { + "ph": "s", "id": 291, "pid": 2338706, "tid": 2338706, "ts": 6413853762756.092, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853762826.602, "dur": 270.942, + "args": { + "External id": 1438602,"Sequence number": 15349045, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [], [], [], [], []], "Ev Idx": 18894 + } + }, + { + "ph": "s", "id": 290, "pid": 2338706, "tid": 2338706, "ts": 6413853762826.602, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853762848.455, "dur": 3.454, + "args": { + "External id": 1438603,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853762849.713, "dur": 1.974, + "args": { + "External id": 1438604,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853762860.113, "dur": 7.283, + "args": { + "External id": 1438605,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853762862.920, "dur": 4.081, + "args": { + "External id": 1438606,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853762873.849, "dur": 4.806, + "args": { + "External id": 1438607,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763041.452, "dur": 4.813, + "args": { + "External id": 1438608,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763042.916, "dur": 3.012, + "args": { + "External id": 1438609,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853763122.152, "dur": 113.784, + "args": { + "External id": 1438610,"Sequence number": 15349046, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853763123.302, "dur": 10.436, + "args": { + "External id": 1438611,"Sequence number": 15349046, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18903 + } + }, + { + "ph": "s", "id": 289, "pid": 2338706, "tid": 2338706, "ts": 6413853763123.302, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853763126.856, "dur": 5.108, + "args": { + "External id": 1438612,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853763129.933, "dur": 1.780, + "args": { + "External id": 1438613,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853763135.047, "dur": 100.605, + "args": { + "External id": 1438614,"Sequence number": 15349047, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763136.781, "dur": 6.201, + "args": { + "External id": 1438615,"Sequence number": 15349047, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763138.356, "dur": 4.434, + "args": { + "External id": 1438616,"Sequence number": 15349047, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18908 + } + }, + { + "ph": "s", "id": 288, "pid": 2338706, "tid": 2338706, "ts": 6413853763138.356, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853763143.747, "dur": 84.257, + "args": { + "External id": 1438617,"Sequence number": 15349048, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18909 + } + }, + { + "ph": "s", "id": 287, "pid": 2338706, "tid": 2338706, "ts": 6413853763143.747, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763230.543, "dur": 4.273, + "args": { + "External id": 1438618,"Sequence number": 15349049, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18910 + } + }, + { + "ph": "s", "id": 286, "pid": 2338706, "tid": 2338706, "ts": 6413853763230.543, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853763246.792, "dur": 66.141, + "args": { + "External id": 1438619,"Sequence number": 15349050, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853763247.483, "dur": 5.901, + "args": { + "External id": 1438620,"Sequence number": 15349050, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18912 + } + }, + { + "ph": "s", "id": 285, "pid": 2338706, "tid": 2338706, "ts": 6413853763247.483, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853763249.144, "dur": 2.907, + "args": { + "External id": 1438621,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853763250.729, "dur": 1.166, + "args": { + "External id": 1438622,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853763253.998, "dur": 58.670, + "args": { + "External id": 1438623,"Sequence number": 15349051, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763255.338, "dur": 5.195, + "args": { + "External id": 1438624,"Sequence number": 15349051, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763256.390, "dur": 3.967, + "args": { + "External id": 1438625,"Sequence number": 15349051, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18917 + } + }, + { + "ph": "s", "id": 284, "pid": 2338706, "tid": 2338706, "ts": 6413853763256.390, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853763261.163, "dur": 45.563, + "args": { + "External id": 1438626,"Sequence number": 15349052, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18918 + } + }, + { + "ph": "s", "id": 283, "pid": 2338706, "tid": 2338706, "ts": 6413853763261.163, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763308.817, "dur": 3.375, + "args": { + "External id": 1438627,"Sequence number": 15349053, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18919 + } + }, + { + "ph": "s", "id": 282, "pid": 2338706, "tid": 2338706, "ts": 6413853763308.817, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853763321.411, "dur": 66.502, + "args": { + "External id": 1438628,"Sequence number": 15349054, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [1024, 4096], []], "Ev Idx": 18920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853763322.342, "dur": 5.089, + "args": { + "External id": 1438629,"Sequence number": 15349054, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[1024, 4096]], "Ev Idx": 18921 + } + }, + { + "ph": "s", "id": 281, "pid": 2338706, "tid": 2338706, "ts": 6413853763322.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853763324.034, "dur": 2.336, + "args": { + "External id": 1438630,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1024, 4096], [], []], "Ev Idx": 18922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853763325.306, "dur": 0.913, + "args": { + "External id": 1438631,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1024]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1024, 4096], [], [], []], "Ev Idx": 18923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853763328.281, "dur": 59.418, + "args": { + "External id": 1438632,"Sequence number": 15349055, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 1024]], "Ev Idx": 18924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763329.964, "dur": 6.292, + "args": { + "External id": 1438633,"Sequence number": 15349055, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763330.906, "dur": 5.162, + "args": { + "External id": 1438634,"Sequence number": 15349055, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18926 + } + }, + { + "ph": "s", "id": 280, "pid": 2338706, "tid": 2338706, "ts": 6413853763330.906, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853763336.826, "dur": 45.532, + "args": { + "External id": 1438635,"Sequence number": 15349056, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 1024]], "Ev Idx": 18927 + } + }, + { + "ph": "s", "id": 279, "pid": 2338706, "tid": 2338706, "ts": 6413853763336.826, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763383.971, "dur": 3.295, + "args": { + "External id": 1438636,"Sequence number": 15349057, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 1024]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1024, 1], []], "Input Dims": [[32768, 1024], []], "Ev Idx": 18928 + } + }, + { + "ph": "s", "id": 278, "pid": 2338706, "tid": 2338706, "ts": 6413853763383.971, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763405.618, "dur": 5.324, + "args": { + "External id": 1438637,"Sequence number": 15349058, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763406.796, "dur": 3.964, + "args": { + "External id": 1438638,"Sequence number": 15349058, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 32, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18930 + } + }, + { + "ph": "s", "id": 277, "pid": 2338706, "tid": 2338706, "ts": 6413853763406.796, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763419.172, "dur": 5.510, + "args": { + "External id": 1438639,"Sequence number": 15349059, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763420.652, "dur": 3.856, + "args": { + "External id": 1438640,"Sequence number": 15349059, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18932 + } + }, + { + "ph": "s", "id": 276, "pid": 2338706, "tid": 2338706, "ts": 6413853763420.652, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853763429.324, "dur": 4.945, + "args": { + "External id": 1438641,"Sequence number": 15349060, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853763430.834, "dur": 3.259, + "args": { + "External id": 1438642,"Sequence number": 15349060, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 8, 128]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4194304, 1024, 1], []], "Input Dims": [[8, 4096, 1024], []], "Ev Idx": 18934 + } + }, + { + "ph": "s", "id": 275, "pid": 2338706, "tid": 2338706, "ts": 6413853763430.834, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853763467.376, "dur": 177.113, + "args": { + "External id": 1438643,"Sequence number": 15349061, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18935 + } + }, + { + "ph": "s", "id": 274, "pid": 2338706, "tid": 2338706, "ts": 6413853763467.376, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853763489.232, "dur": 10.397, + "args": { + "External id": 1438644,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853763492.776, "dur": 6.450, + "args": { + "External id": 1438645,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853763659.535, "dur": 118.669, + "args": { + "External id": 1438646,"Sequence number": 15349062, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "4096"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[4194304, 1024, 128, 1], [64, 1], [64, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [4096, 64], [4096, 64], [], [], [], [], []], "Ev Idx": 18938 + } + }, + { + "ph": "s", "id": 273, "pid": 2338706, "tid": 2338706, "ts": 6413853763659.535, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853763674.421, "dur": 7.474, + "args": { + "External id": 1438647,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4194304, 1024, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 8, 128], [], [], [], [], []], "Ev Idx": 18939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853763676.757, "dur": 4.761, + "args": { + "External id": 1438648,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 8, 128]", "[4194304, 1024, 128, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 2338706, "tid": 2338706, + "ts": 6413853763807.969, "dur": 224.221, + "args": { + "External id": 1438649,"Sequence number": 15349063, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], [], []], "Ev Idx": 18941 + } + }, + { + "ph": "s", "id": 272, "pid": 2338706, "tid": 2338706, "ts": 6413853763807.969, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413853763838.058, "dur": 136.035, + "args": { + "External id": 1438650,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.088388347648318447", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[16777216, 4096, 128, 1], [4194304, 1024, 128, 1], [4194304, 1024, 128, 1], [], [], [], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [8, 4096, 8, 128], [8, 4096, 8, 128], [], [], [], [], [], [], [], []], "Ev Idx": 18942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853763892.983, "dur": 6.914, + "args": { + "External id": 1438651,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[16777216, 4096, 128, 1], [], [], [], [], []], "Input Dims": [[8, 4096, 32, 128], [], [], [], [], []], "Ev Idx": 18943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853763895.541, "dur": 3.878, + "args": { + "External id": 1438652,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 32, 128]", "[16777216, 4096, 128, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853763903.340, "dur": 3.655, + "args": { + "External id": 1438653,"Record function id": 0, "Concrete Inputs": ["[8, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853763908.543, "dur": 1.306, + "args": { + "External id": 1438654,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853763912.772, "dur": 3.904, + "args": { + "External id": 1438655,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 2338706, "tid": 2338706, + "ts": 6413853764009.977, "dur": 5.579, + "args": { + "External id": 1438656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[16777216, 4096, 128, 1]], "Input Dims": [[8, 4096, 32, 128]], "Ev Idx": 18948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764038.665, "dur": 7.242, + "args": { + "External id": 1438657,"Sequence number": 15349064, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764040.729, "dur": 4.961, + "args": { + "External id": 1438658,"Sequence number": 15349064, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 128, 1], []], "Input Dims": [[8, 4096, 32, 128], []], "Ev Idx": 18950 + } + }, + { + "ph": "s", "id": 271, "pid": 2338706, "tid": 2338706, "ts": 6413853764040.729, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853764098.398, "dur": 123.149, + "args": { + "External id": 1438659,"Sequence number": 15349065, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [4096, 4096], []], "Ev Idx": 18951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853764099.701, "dur": 11.045, + "args": { + "External id": 1438660,"Sequence number": 15349065, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[4096, 4096]], "Ev Idx": 18952 + } + }, + { + "ph": "s", "id": 270, "pid": 2338706, "tid": 2338706, "ts": 6413853764099.701, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853764103.311, "dur": 5.720, + "args": { + "External id": 1438661,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[4096, 4096], [], []], "Ev Idx": 18953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853764106.790, "dur": 1.801, + "args": { + "External id": 1438662,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[4096, 4096], [], [], []], "Ev Idx": 18954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853764112.051, "dur": 109.188, + "args": { + "External id": 1438663,"Sequence number": 15349066, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 4096]], "Ev Idx": 18955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764113.940, "dur": 5.298, + "args": { + "External id": 1438664,"Sequence number": 15349066, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764114.756, "dur": 4.254, + "args": { + "External id": 1438665,"Sequence number": 15349066, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18957 + } + }, + { + "ph": "s", "id": 269, "pid": 2338706, "tid": 2338706, "ts": 6413853764114.756, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853764120.426, "dur": 92.699, + "args": { + "External id": 1438666,"Sequence number": 15349067, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 4096]], "Ev Idx": 18958 + } + }, + { + "ph": "s", "id": 268, "pid": 2338706, "tid": 2338706, "ts": 6413853764120.426, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764215.768, "dur": 4.589, + "args": { + "External id": 1438667,"Sequence number": 15349068, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18959 + } + }, + { + "ph": "s", "id": 267, "pid": 2338706, "tid": 2338706, "ts": 6413853764215.768, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853764271.017, "dur": 242.398, + "args": { + "External id": 1438668,"Sequence number": 15349069, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16777216, 4096, 1], [1], [], [16777216, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [4096], [], [8, 4096, 4096], [], [], [], []], "Ev Idx": 18960 + } + }, + { + "ph": "s", "id": 266, "pid": 2338706, "tid": 2338706, "ts": 6413853764271.017, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764293.855, "dur": 2.745, + "args": { + "External id": 1438669,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764294.709, "dur": 1.687, + "args": { + "External id": 1438670,"Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 2338706, "tid": 2338706, + "ts": 6413853764301.162, "dur": 5.807, + "args": { + "External id": 1438671,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [4096, 1]], "Input Dims": [[8, 4096, 4096], [32768, 4096]], "Ev Idx": 18963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764302.131, "dur": 4.716, + "args": { + "External id": 1438672,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764303.256, "dur": 3.466, + "args": { + "External id": 1438673,"Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853764315.900, "dur": 11.788, + "args": { + "External id": 1438674,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 18966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853764321.355, "dur": 5.976, + "args": { + "External id": 1438675,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853764334.854, "dur": 3.655, + "args": { + "External id": 1438676,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853764342.870, "dur": 3.630, + "args": { + "External id": 1438677,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764488.418, "dur": 3.562, + "args": { + "External id": 1438678,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764489.995, "dur": 1.700, + "args": { + "External id": 1438679,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764495.110, "dur": 4.929, + "args": { + "External id": 1438680,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764498.708, "dur": 1.218, + "args": { + "External id": 1438681,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 18973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853764532.580, "dur": 102.664, + "args": { + "External id": 1438682,"Sequence number": 15349070, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853764533.794, "dur": 7.600, + "args": { + "External id": 1438683,"Sequence number": 15349070, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18975 + } + }, + { + "ph": "s", "id": 265, "pid": 2338706, "tid": 2338706, "ts": 6413853764533.794, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853764536.509, "dur": 3.714, + "args": { + "External id": 1438684,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853764538.586, "dur": 1.379, + "args": { + "External id": 1438685,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853764542.530, "dur": 92.406, + "args": { + "External id": 1438686,"Sequence number": 15349071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764544.230, "dur": 7.163, + "args": { + "External id": 1438687,"Sequence number": 15349071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764547.612, "dur": 3.615, + "args": { + "External id": 1438688,"Sequence number": 15349071, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18980 + } + }, + { + "ph": "s", "id": 264, "pid": 2338706, "tid": 2338706, "ts": 6413853764547.612, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853764552.130, "dur": 75.374, + "args": { + "External id": 1438689,"Sequence number": 15349072, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18981 + } + }, + { + "ph": "s", "id": 263, "pid": 2338706, "tid": 2338706, "ts": 6413853764552.130, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764629.971, "dur": 4.155, + "args": { + "External id": 1438690,"Sequence number": 15349073, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18982 + } + }, + { + "ph": "s", "id": 262, "pid": 2338706, "tid": 2338706, "ts": 6413853764629.971, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853764644.707, "dur": 93.347, + "args": { + "External id": 1438691,"Sequence number": 15349074, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[16777216, 4096, 1], [4096, 1], []], "Input Dims": [[8, 4096, 4096], [14336, 4096], []], "Ev Idx": 18983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853764645.494, "dur": 9.116, + "args": { + "External id": 1438692,"Sequence number": 15349074, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[14336, 4096]], "Ev Idx": 18984 + } + }, + { + "ph": "s", "id": 261, "pid": 2338706, "tid": 2338706, "ts": 6413853764645.494, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853764650.444, "dur": 3.056, + "args": { + "External id": 1438693,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[14336, 4096], [], []], "Ev Idx": 18985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853764652.210, "dur": 1.130, + "args": { + "External id": 1438694,"Record function id": 0, "Concrete Inputs": ["", "[4096, 14336]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[14336, 4096], [], [], []], "Ev Idx": 18986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853764655.445, "dur": 82.364, + "args": { + "External id": 1438695,"Sequence number": 15349075, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[16777216, 4096, 1], [1, 4096]], "Input Dims": [[8, 4096, 4096], [4096, 14336]], "Ev Idx": 18987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764656.838, "dur": 9.349, + "args": { + "External id": 1438696,"Sequence number": 15349075, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764657.850, "dur": 8.151, + "args": { + "External id": 1438697,"Sequence number": 15349075, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[32768, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 18989 + } + }, + { + "ph": "s", "id": 260, "pid": 2338706, "tid": 2338706, "ts": 6413853764657.850, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853764666.802, "dur": 65.168, + "args": { + "External id": 1438698,"Sequence number": 15349076, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[32768, 4096], [4096, 14336]], "Ev Idx": 18990 + } + }, + { + "ph": "s", "id": 259, "pid": 2338706, "tid": 2338706, "ts": 6413853764666.802, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764734.217, "dur": 3.117, + "args": { + "External id": 1438699,"Sequence number": 15349077, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[14336, 1], []], "Input Dims": [[32768, 14336], []], "Ev Idx": 18991 + } + }, + { + "ph": "s", "id": 258, "pid": 2338706, "tid": 2338706, "ts": 6413853764734.217, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853764760.510, "dur": 162.965, + "args": { + "External id": 1438700,"Sequence number": 15349078, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18992 + } + }, + { + "ph": "s", "id": 257, "pid": 2338706, "tid": 2338706, "ts": 6413853764760.510, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853764802.402, "dur": 5.430, + "args": { + "External id": 1438701,"Record function id": 0, "Concrete Inputs": ["[8, 4096, 14336]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 18993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853764845.861, "dur": 64.226, + "args": { + "External id": 1438702,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[58720256, 14336, 1], [14336, 1], []], "Input Dims": [[8, 4096, 14336], [4096, 14336], []], "Ev Idx": 18994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853764847.077, "dur": 4.794, + "args": { + "External id": 1438703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[14336, 1]], "Input Dims": [[4096, 14336]], "Ev Idx": 18995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853764848.599, "dur": 2.410, + "args": { + "External id": 1438704,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[14336, 1], [], []], "Input Dims": [[4096, 14336], [], []], "Ev Idx": 18996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853764850.074, "dur": 0.718, + "args": { + "External id": 1438705,"Record function id": 0, "Concrete Inputs": ["", "[14336, 4096]", "[1, 14336]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[14336, 1], [], [], []], "Input Dims": [[4096, 14336], [], [], []], "Ev Idx": 18997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853764852.581, "dur": 57.063, + "args": { + "External id": 1438706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[58720256, 14336, 1], [1, 14336]], "Input Dims": [[8, 4096, 14336], [14336, 4096]], "Ev Idx": 18998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338706, "tid": 2338706, + "ts": 6413853764854.052, "dur": 2.619, + "args": { + "External id": 1438707,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 18999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764855.214, "dur": 1.250, + "args": { + "External id": 1438708,"Record function id": 0, "Concrete Inputs": ["", "[32768, 14336]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[58720256, 14336, 1], []], "Input Dims": [[8, 4096, 14336], []], "Ev Idx": 19000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853764857.306, "dur": 48.088, + "args": { + "External id": 1438709,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[14336, 1], [1, 14336]], "Input Dims": [[32768, 14336], [14336, 4096]], "Ev Idx": 19001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338706, "tid": 2338706, + "ts": 6413853764907.805, "dur": 1.207, + "args": { + "External id": 1438710,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413853764933.606, "dur": 29.860, + "args": { + "External id": 1438711,"Sequence number": 15349079, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[16777216, 4096, 1], [16777216, 4096, 1], []], "Input Dims": [[8, 4096, 4096], [8, 4096, 4096], []], "Ev Idx": 19003 + } + }, + { + "ph": "s", "id": 256, "pid": 2338706, "tid": 2338706, "ts": 6413853764933.606, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338706, "tid": 2338706, + "ts": 6413853765006.127, "dur": 100.563, + "args": { + "External id": 1438712,"Sequence number": 15349080, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 19004 + } + }, + { + "ph": "s", "id": 255, "pid": 2338706, "tid": 2338706, "ts": 6413853765006.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338706, "tid": 2338706, + "ts": 6413853765016.564, "dur": 78.704, + "args": { + "External id": 1438713,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1], [16777216, 4096, 1]], []], "Input Dims": [[[8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096], [8, 4096, 4096]], []], "Ev Idx": 19005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853765100.013, "dur": 3.709, + "args": { + "External id": 1438714,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 16384], []], "Ev Idx": 19006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 2338706, "tid": 2338706, + "ts": 6413853765150.507, "dur": 53.314, + "args": { + "External id": 1438715,"Record function id": 0, "Ev Idx": 19007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338706, "tid": 2338706, + "ts": 6413853765206.314, "dur": 226.802, + "args": { + "External id": 1438716,"Record function id": 0, "Ev Idx": 19008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853765250.198, "dur": 173.105, + "args": { + "External id": 1438717,"Sequence number": 15349081, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [67108864, 16384, 4096, 1]], "Input Dims": [[4096], [8, 4096, 4, 4096]], "Ev Idx": 19009 + } + }, + { + "ph": "s", "id": 254, "pid": 2338706, "tid": 2338706, "ts": 6413853765250.198, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338706, "tid": 2338706, + "ts": 6413853765329.304, "dur": 49.056, + "args": { + "External id": 1438718,"kernel_hash": "csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/sx/csxej2eqpdr6urgmnplkn2gxd6ebpciul5hudjchjoyne3jkpjo3.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[131072, 4096], [131072, 4096], [4096], [131072], [], [], [], [], [], [], [], [], []], "Ev Idx": 19010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853765529.880, "dur": 118.548, + "args": { + "External id": 1438719,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853765533.686, "dur": 5.894, + "args": { + "External id": 1438720,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765614.935, "dur": 33.063, + "args": { + "External id": 1438721,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 19013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765618.674, "dur": 28.815, + "args": { + "External id": 1438722,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 19014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853765655.422, "dur": 20.385, + "args": { + "External id": 1438723,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853765656.902, "dur": 2.714, + "args": { + "External id": 1438724,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765660.707, "dur": 14.764, + "args": { + "External id": 1438725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 19017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765661.725, "dur": 13.296, + "args": { + "External id": 1438726,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 19018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853765680.392, "dur": 18.524, + "args": { + "External id": 1438727,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853765681.560, "dur": 2.286, + "args": { + "External id": 1438728,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765684.811, "dur": 13.808, + "args": { + "External id": 1438729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 19021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765685.583, "dur": 12.640, + "args": { + "External id": 1438730,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 19022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853765711.508, "dur": 0.784, + "args": { + "External id": 1438731,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[8, 8192], [], [], [], [], [], [], []], "Ev Idx": 19023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 2338706, "tid": 2338706, + "ts": 6413853765721.566, "dur": 11.395, + "args": { + "External id": 1438732,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "5", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 19024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765728.600, "dur": 2.303, + "args": { + "External id": 1438733,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 8192], [], [], []], "Ev Idx": 19025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765740.679, "dur": 9.871, + "args": { + "External id": 1438734,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 19026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765745.076, "dur": 3.375, + "args": { + "External id": 1438735,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 19027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765751.951, "dur": 3.700, + "args": { + "External id": 1438736,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 19028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765754.406, "dur": 0.307, + "args": { + "External id": 1438737,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 19029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765757.156, "dur": 2.829, + "args": { + "External id": 1438738,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 5], [], [], [], []], "Ev Idx": 19030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765759.013, "dur": 0.308, + "args": { + "External id": 1438739,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 5], [], [], []], "Ev Idx": 19031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765763.527, "dur": 3.019, + "args": { + "External id": 1438740,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 19032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765765.479, "dur": 0.427, + "args": { + "External id": 1438741,"Record function id": 0, "Concrete Inputs": ["", "[8, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 19033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765767.796, "dur": 3.086, + "args": { + "External id": 1438742,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 8188, 4], [], [], [], []], "Ev Idx": 19034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765769.686, "dur": 0.399, + "args": { + "External id": 1438743,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 8188, 4], [], [], []], "Ev Idx": 19035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765771.932, "dur": 3.189, + "args": { + "External id": 1438744,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4096, 4], [], [], [], []], "Ev Idx": 19036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765774.063, "dur": 0.445, + "args": { + "External id": 1438745,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 19037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853765779.355, "dur": 5.291, + "args": { + "External id": 1438746,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4096, 4], [], []], "Ev Idx": 19038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765783.327, "dur": 0.394, + "args": { + "External id": 1438747,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4096, 4], [], [], []], "Ev Idx": 19039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765789.727, "dur": 2.986, + "args": { + "External id": 1438748,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 19040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765791.568, "dur": 0.449, + "args": { + "External id": 1438749,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853765795.808, "dur": 9.818, + "args": { + "External id": 1438750,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 19042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765801.099, "dur": 2.983, + "args": { + "External id": 1438751,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765806.947, "dur": 5.184, + "args": { + "External id": 1438752,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 19044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765811.026, "dur": 0.439, + "args": { + "External id": 1438753,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 19045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765815.097, "dur": 6.589, + "args": { + "External id": 1438754,"Sequence number": 15349082, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19046 + } + }, + { + "ph": "s", "id": 253, "pid": 2338706, "tid": 2338706, "ts": 6413853765815.097, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765819.219, "dur": 0.693, + "args": { + "External id": 1438755,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765822.800, "dur": 4.326, + "args": { + "External id": 1438756,"Sequence number": 15349083, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19048 + } + }, + { + "ph": "s", "id": 252, "pid": 2338706, "tid": 2338706, "ts": 6413853765822.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765825.633, "dur": 0.625, + "args": { + "External id": 1438757,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853765830.347, "dur": 5.405, + "args": { + "External id": 1438758,"Sequence number": 15349084, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 19050 + } + }, + { + "ph": "s", "id": 251, "pid": 2338706, "tid": 2338706, "ts": 6413853765830.347, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765834.125, "dur": 0.504, + "args": { + "External id": 1438759,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853765836.978, "dur": 4.423, + "args": { + "External id": 1438760,"Sequence number": 15349085, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 19052 + } + }, + { + "ph": "s", "id": 250, "pid": 2338706, "tid": 2338706, "ts": 6413853765836.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853765839.888, "dur": 0.608, + "args": { + "External id": 1438761,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 19053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853765845.541, "dur": 41.869, + "args": { + "External id": 1438762,"Sequence number": 15349086, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853765847.266, "dur": 39.781, + "args": { + "External id": 1438763,"Sequence number": 15349086, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853765850.086, "dur": 7.191, + "args": { + "External id": 1438764,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 19056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853765852.122, "dur": 4.466, + "args": { + "External id": 1438765,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853765861.230, "dur": 25.162, + "args": { + "External id": 1438766,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 19058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853765916.647, "dur": 4.495, + "args": { + "External id": 1438767,"Sequence number": 15349086, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 19059 + } + }, + { + "ph": "s", "id": 249, "pid": 2338706, "tid": 2338706, "ts": 6413853765916.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853765923.411, "dur": 3.694, + "args": { + "External id": 1438768,"Sequence number": 15349087, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853765956.588, "dur": 126922.323, + "args": { + "External id": 1438769,"Sequence number": 15349087, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 19061 + } + }, + { + "ph": "s", "id": 248, "pid": 2338706, "tid": 2338706, "ts": 6413853765956.588, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853765972.871, "dur": 59.580, + "args": { + "External id": 1438770,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853765973.534, "dur": 58.577, + "args": { + "External id": 1438771,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853765975.164, "dur": 31.984, + "args": { + "External id": 1438772,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853765999.986, "dur": 6.430, + "args": { + "External id": 1438773,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766008.355, "dur": 23.267, + "args": { + "External id": 1438774,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 19066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853766053.442, "dur": 68.657, + "args": { + "External id": 1438775,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853766091.760, "dur": 10.004, + "args": { + "External id": 1438776,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853766095.929, "dur": 5.225, + "args": { + "External id": 1438777,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766102.794, "dur": 19.083, + "args": { + "External id": 1438778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766103.882, "dur": 17.549, + "args": { + "External id": 1438779,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853766127.255, "dur": 21.067, + "args": { + "External id": 1438780,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853766128.457, "dur": 4.952, + "args": { + "External id": 1438781,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853766129.821, "dur": 3.287, + "args": { + "External id": 1438782,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766133.968, "dur": 14.125, + "args": { + "External id": 1438783,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766137.036, "dur": 10.679, + "args": { + "External id": 1438784,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 19076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853766154.466, "dur": 19.984, + "args": { + "External id": 1438785,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853766155.955, "dur": 4.081, + "args": { + "External id": 1438786,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766160.900, "dur": 13.252, + "args": { + "External id": 1438787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 19079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766161.428, "dur": 12.379, + "args": { + "External id": 1438788,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413853766180.983, "dur": 34.649, + "args": { + "External id": 1438789,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853766219.951, "dur": 73.055, + "args": { + "External id": 1438790,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853766222.892, "dur": 69.517, + "args": { + "External id": 1438791,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853766229.690, "dur": 1.136, + "args": { + "External id": 1438792,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853766237.088, "dur": 31.793, + "args": { + "External id": 1438793,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853766239.068, "dur": 29.472, + "args": { + "External id": 1438794,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 19086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853766243.562, "dur": 5.773, + "args": { + "External id": 1438795,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853766250.405, "dur": 17.599, + "args": { + "External id": 1438796,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 19088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413853766298.942, "dur": 119481.063, + "args": { + "External id": 1438797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413853766301.102, "dur": 119475.443, + "args": { + "External id": 1438798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853885811.175, "dur": 15.518, + "args": { + "External id": 1438799,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853885821.029, "dur": 2.299, + "args": { + "External id": 1438800,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853885834.715, "dur": 162.288, + "args": { + "External id": 1438801,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853885837.334, "dur": 11.037, + "args": { + "External id": 1438802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853885843.410, "dur": 3.838, + "args": { + "External id": 1438803,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853885845.524, "dur": 1.371, + "args": { + "External id": 1438804,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853885849.845, "dur": 146.118, + "args": { + "External id": 1438805,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853885852.399, "dur": 141.820, + "args": { + "External id": 1438806,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853886004.994, "dur": 7.511, + "args": { + "External id": 1438807,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853886009.125, "dur": 1.192, + "args": { + "External id": 1438808,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853886026.931, "dur": 5.320, + "args": { + "External id": 1438809,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853886049.325, "dur": 60.558, + "args": { + "External id": 1438810,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853886100.409, "dur": 8.818, + "args": { + "External id": 1438811,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853886291.439, "dur": 285.380, + "args": { + "External id": 1438812,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853886296.019, "dur": 2.571, + "args": { + "External id": 1438813,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853886302.400, "dur": 273.560, + "args": { + "External id": 1438814,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853886307.916, "dur": 0.713, + "args": { + "External id": 1438815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853886313.007, "dur": 38.153, + "args": { + "External id": 1438816,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853886353.606, "dur": 6.175, + "args": { + "External id": 1438817,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853886357.855, "dur": 1.358, + "args": { + "External id": 1438818,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853886361.371, "dur": 33.060, + "args": { + "External id": 1438819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853886364.190, "dur": 1.234, + "args": { + "External id": 1438820,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853886368.746, "dur": 25.249, + "args": { + "External id": 1438821,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886373.906, "dur": 3.712, + "args": { + "External id": 1438822,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853886397.053, "dur": 32.334, + "args": { + "External id": 1438823,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886433.220, "dur": 21.882, + "args": { + "External id": 1438824,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853886460.690, "dur": 23.018, + "args": { + "External id": 1438825,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886488.679, "dur": 18.042, + "args": { + "External id": 1438826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853886509.635, "dur": 27.733, + "args": { + "External id": 1438827,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886512.809, "dur": 1.990, + "args": { + "External id": 1438828,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853886517.265, "dur": 0.584, + "args": { + "External id": 1438829,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886539.229, "dur": 17.459, + "args": { + "External id": 1438830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886558.494, "dur": 16.089, + "args": { + "External id": 1438831,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853886588.530, "dur": 4.521, + "args": { + "External id": 1438832,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853886603.548, "dur": 6.035, + "args": { + "External id": 1438833,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853886607.876, "dur": 0.399, + "args": { + "External id": 1438834,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853886710.488, "dur": 98.096, + "args": { + "External id": 1438835,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853886815.018, "dur": 8.008, + "args": { + "External id": 1438836,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853886819.003, "dur": 2.489, + "args": { + "External id": 1438837,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886825.346, "dur": 34.340, + "args": { + "External id": 1438838,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853886866.829, "dur": 11.788, + "args": { + "External id": 1438839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853886872.688, "dur": 4.483, + "args": { + "External id": 1438840,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853886875.119, "dur": 1.149, + "args": { + "External id": 1438841,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853886883.686, "dur": 63.724, + "args": { + "External id": 1438842,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853886885.059, "dur": 61.538, + "args": { + "External id": 1438843,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853886954.752, "dur": 18.920, + "args": { + "External id": 1438844,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853887002.240, "dur": 11.262, + "args": { + "External id": 1438845,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887009.586, "dur": 0.920, + "args": { + "External id": 1438846,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853887020.128, "dur": 105.885, + "args": { + "External id": 1438847,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853887021.448, "dur": 5.513, + "args": { + "External id": 1438848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853887022.920, "dur": 3.275, + "args": { + "External id": 1438849,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887025.366, "dur": 0.601, + "args": { + "External id": 1438850,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853887027.761, "dur": 97.498, + "args": { + "External id": 1438851,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853887028.642, "dur": 95.173, + "args": { + "External id": 1438852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853887137.446, "dur": 7.177, + "args": { + "External id": 1438853,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887141.917, "dur": 0.785, + "args": { + "External id": 1438854,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853887153.932, "dur": 2.496, + "args": { + "External id": 1438855,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853887168.981, "dur": 8.685, + "args": { + "External id": 1438856,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853887171.368, "dur": 5.992, + "args": { + "External id": 1438857,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853887310.470, "dur": 237.303, + "args": { + "External id": 1438858,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853887314.350, "dur": 3.167, + "args": { + "External id": 1438859,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853887319.854, "dur": 227.303, + "args": { + "External id": 1438860,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853887321.857, "dur": 0.647, + "args": { + "External id": 1438861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853887323.958, "dur": 29.063, + "args": { + "External id": 1438862,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853887354.853, "dur": 6.244, + "args": { + "External id": 1438863,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887357.500, "dur": 3.253, + "args": { + "External id": 1438864,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853887362.364, "dur": 31.032, + "args": { + "External id": 1438865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853887363.862, "dur": 1.391, + "args": { + "External id": 1438866,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853887366.553, "dur": 26.514, + "args": { + "External id": 1438867,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887372.655, "dur": 2.961, + "args": { + "External id": 1438868,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853887395.528, "dur": 26.005, + "args": { + "External id": 1438869,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887424.169, "dur": 19.152, + "args": { + "External id": 1438870,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853887446.733, "dur": 17.349, + "args": { + "External id": 1438871,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887465.804, "dur": 18.256, + "args": { + "External id": 1438872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853887486.263, "dur": 24.849, + "args": { + "External id": 1438873,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887488.796, "dur": 2.341, + "args": { + "External id": 1438874,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887493.619, "dur": 0.753, + "args": { + "External id": 1438875,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887515.190, "dur": 16.016, + "args": { + "External id": 1438876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887532.742, "dur": 13.032, + "args": { + "External id": 1438877,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853887555.820, "dur": 2.209, + "args": { + "External id": 1438878,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853887571.079, "dur": 5.601, + "args": { + "External id": 1438879,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887574.973, "dur": 0.547, + "args": { + "External id": 1438880,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853887666.598, "dur": 78.345, + "args": { + "External id": 1438881,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853887751.497, "dur": 5.986, + "args": { + "External id": 1438882,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887755.383, "dur": 0.804, + "args": { + "External id": 1438883,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887759.426, "dur": 30.355, + "args": { + "External id": 1438884,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853887798.046, "dur": 6.696, + "args": { + "External id": 1438885,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853887800.237, "dur": 3.779, + "args": { + "External id": 1438886,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887802.609, "dur": 1.131, + "args": { + "External id": 1438887,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853887808.247, "dur": 55.532, + "args": { + "External id": 1438888,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853887809.449, "dur": 53.646, + "args": { + "External id": 1438889,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853887868.872, "dur": 30.098, + "args": { + "External id": 1438890,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853887905.929, "dur": 9.477, + "args": { + "External id": 1438891,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887913.674, "dur": 0.714, + "args": { + "External id": 1438892,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853887920.322, "dur": 81.266, + "args": { + "External id": 1438893,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853887921.448, "dur": 5.032, + "args": { + "External id": 1438894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853887922.553, "dur": 3.172, + "args": { + "External id": 1438895,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853887924.414, "dur": 1.044, + "args": { + "External id": 1438896,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853887927.335, "dur": 73.563, + "args": { + "External id": 1438897,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853887930.833, "dur": 68.521, + "args": { + "External id": 1438898,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853888010.413, "dur": 8.612, + "args": { + "External id": 1438899,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888014.183, "dur": 3.297, + "args": { + "External id": 1438900,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853888027.904, "dur": 2.425, + "args": { + "External id": 1438901,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853888040.621, "dur": 7.657, + "args": { + "External id": 1438902,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853888043.348, "dur": 4.622, + "args": { + "External id": 1438903,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853888236.102, "dur": 232.477, + "args": { + "External id": 1438904,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853888240.816, "dur": 3.633, + "args": { + "External id": 1438905,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853888246.412, "dur": 221.487, + "args": { + "External id": 1438906,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853888248.368, "dur": 0.545, + "args": { + "External id": 1438907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853888250.621, "dur": 27.394, + "args": { + "External id": 1438908,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853888279.748, "dur": 4.284, + "args": { + "External id": 1438909,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888282.784, "dur": 0.864, + "args": { + "External id": 1438910,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853888285.115, "dur": 31.376, + "args": { + "External id": 1438911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853888286.864, "dur": 1.238, + "args": { + "External id": 1438912,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853888292.550, "dur": 23.432, + "args": { + "External id": 1438913,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888297.492, "dur": 3.370, + "args": { + "External id": 1438914,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853888318.452, "dur": 29.825, + "args": { + "External id": 1438915,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888349.992, "dur": 17.592, + "args": { + "External id": 1438916,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853888371.407, "dur": 17.123, + "args": { + "External id": 1438917,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888390.235, "dur": 14.975, + "args": { + "External id": 1438918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853888407.763, "dur": 26.310, + "args": { + "External id": 1438919,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888410.283, "dur": 1.967, + "args": { + "External id": 1438920,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888414.828, "dur": 0.767, + "args": { + "External id": 1438921,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888435.906, "dur": 15.297, + "args": { + "External id": 1438922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888452.616, "dur": 14.053, + "args": { + "External id": 1438923,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853888479.119, "dur": 2.615, + "args": { + "External id": 1438924,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853888493.370, "dur": 6.035, + "args": { + "External id": 1438925,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888497.139, "dur": 1.182, + "args": { + "External id": 1438926,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853888581.883, "dur": 72.792, + "args": { + "External id": 1438927,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853888660.814, "dur": 5.289, + "args": { + "External id": 1438928,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888664.295, "dur": 0.726, + "args": { + "External id": 1438929,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888667.829, "dur": 30.935, + "args": { + "External id": 1438930,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853888704.069, "dur": 8.161, + "args": { + "External id": 1438931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853888707.936, "dur": 3.557, + "args": { + "External id": 1438932,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888710.445, "dur": 0.836, + "args": { + "External id": 1438933,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853888715.425, "dur": 48.288, + "args": { + "External id": 1438934,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853888716.847, "dur": 45.982, + "args": { + "External id": 1438935,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853888768.790, "dur": 15.430, + "args": { + "External id": 1438936,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853888790.832, "dur": 6.458, + "args": { + "External id": 1438937,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888795.662, "dur": 0.682, + "args": { + "External id": 1438938,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853888802.424, "dur": 50.046, + "args": { + "External id": 1438939,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853888803.474, "dur": 4.732, + "args": { + "External id": 1438940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853888804.444, "dur": 3.078, + "args": { + "External id": 1438941,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888806.422, "dur": 0.915, + "args": { + "External id": 1438942,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853888809.103, "dur": 42.877, + "args": { + "External id": 1438943,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853888809.818, "dur": 41.537, + "args": { + "External id": 1438944,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853888859.395, "dur": 4.061, + "args": { + "External id": 1438945,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853888861.690, "dur": 0.514, + "args": { + "External id": 1438946,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853888870.099, "dur": 1.574, + "args": { + "External id": 1438947,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853888880.233, "dur": 9.497, + "args": { + "External id": 1438948,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853888883.093, "dur": 6.314, + "args": { + "External id": 1438949,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853889017.174, "dur": 269.637, + "args": { + "External id": 1438950,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853889019.912, "dur": 3.295, + "args": { + "External id": 1438951,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853889024.839, "dur": 261.453, + "args": { + "External id": 1438952,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853889026.566, "dur": 0.606, + "args": { + "External id": 1438953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853889028.442, "dur": 86.356, + "args": { + "External id": 1438954,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853889118.512, "dur": 5.140, + "args": { + "External id": 1438955,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889122.114, "dur": 1.214, + "args": { + "External id": 1438956,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853889124.798, "dur": 28.809, + "args": { + "External id": 1438957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853889126.451, "dur": 2.140, + "args": { + "External id": 1438958,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853889130.549, "dur": 22.675, + "args": { + "External id": 1438959,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889135.002, "dur": 3.189, + "args": { + "External id": 1438960,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853889155.230, "dur": 24.932, + "args": { + "External id": 1438961,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889181.875, "dur": 16.637, + "args": { + "External id": 1438962,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853889201.828, "dur": 14.707, + "args": { + "External id": 1438963,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889218.199, "dur": 14.437, + "args": { + "External id": 1438964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853889234.677, "dur": 22.590, + "args": { + "External id": 1438965,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889237.374, "dur": 1.938, + "args": { + "External id": 1438966,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889241.625, "dur": 0.668, + "args": { + "External id": 1438967,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889259.465, "dur": 13.027, + "args": { + "External id": 1438968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889273.787, "dur": 11.143, + "args": { + "External id": 1438969,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853889296.108, "dur": 2.943, + "args": { + "External id": 1438970,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853889311.564, "dur": 4.451, + "args": { + "External id": 1438971,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889314.624, "dur": 0.495, + "args": { + "External id": 1438972,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853889403.228, "dur": 72.809, + "args": { + "External id": 1438973,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853889484.455, "dur": 6.311, + "args": { + "External id": 1438974,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889488.695, "dur": 0.902, + "args": { + "External id": 1438975,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889492.252, "dur": 29.182, + "args": { + "External id": 1438976,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853889526.883, "dur": 5.928, + "args": { + "External id": 1438977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853889528.659, "dur": 3.401, + "args": { + "External id": 1438978,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889531.121, "dur": 0.716, + "args": { + "External id": 1438979,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853889537.999, "dur": 49.110, + "args": { + "External id": 1438980,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853889539.470, "dur": 46.884, + "args": { + "External id": 1438981,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889591.982, "dur": 17.608, + "args": { + "External id": 1438982,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853889616.458, "dur": 4.745, + "args": { + "External id": 1438983,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889619.560, "dur": 0.730, + "args": { + "External id": 1438984,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853889625.826, "dur": 54.251, + "args": { + "External id": 1438985,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853889627.169, "dur": 8.809, + "args": { + "External id": 1438986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853889630.680, "dur": 4.620, + "args": { + "External id": 1438987,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889632.184, "dur": 2.945, + "args": { + "External id": 1438988,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853889636.700, "dur": 42.887, + "args": { + "External id": 1438989,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853889637.426, "dur": 41.430, + "args": { + "External id": 1438990,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853889684.580, "dur": 4.336, + "args": { + "External id": 1438991,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889687.001, "dur": 0.690, + "args": { + "External id": 1438992,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853889695.836, "dur": 1.678, + "args": { + "External id": 1438993,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853889708.367, "dur": 6.654, + "args": { + "External id": 1438994,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853889710.905, "dur": 3.822, + "args": { + "External id": 1438995,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853889812.396, "dur": 223.021, + "args": { + "External id": 1438996,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853889814.625, "dur": 2.238, + "args": { + "External id": 1438997,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853889818.430, "dur": 216.409, + "args": { + "External id": 1438998,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853889819.772, "dur": 0.866, + "args": { + "External id": 1438999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853889824.374, "dur": 24.253, + "args": { + "External id": 1439000,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853889850.222, "dur": 4.534, + "args": { + "External id": 1439001,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889853.472, "dur": 1.065, + "args": { + "External id": 1439002,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853889855.581, "dur": 23.983, + "args": { + "External id": 1439003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853889857.141, "dur": 1.160, + "args": { + "External id": 1439004,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853889860.004, "dur": 19.200, + "args": { + "External id": 1439005,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889863.291, "dur": 2.711, + "args": { + "External id": 1439006,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853889881.020, "dur": 22.345, + "args": { + "External id": 1439007,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889904.906, "dur": 15.546, + "args": { + "External id": 1439008,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853889923.832, "dur": 14.783, + "args": { + "External id": 1439009,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889940.345, "dur": 14.536, + "args": { + "External id": 1439010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853889957.338, "dur": 45.050, + "args": { + "External id": 1439011,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853889959.895, "dur": 1.650, + "args": { + "External id": 1439012,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853889964.185, "dur": 0.772, + "args": { + "External id": 1439013,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890005.592, "dur": 14.751, + "args": { + "External id": 1439014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890021.513, "dur": 12.028, + "args": { + "External id": 1439015,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853890044.699, "dur": 2.939, + "args": { + "External id": 1439016,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853890097.368, "dur": 7.168, + "args": { + "External id": 1439017,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890102.254, "dur": 0.954, + "args": { + "External id": 1439018,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853890190.096, "dur": 64.650, + "args": { + "External id": 1439019,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853890304.144, "dur": 7.061, + "args": { + "External id": 1439020,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890308.466, "dur": 1.122, + "args": { + "External id": 1439021,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890312.888, "dur": 28.913, + "args": { + "External id": 1439022,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853890347.916, "dur": 9.033, + "args": { + "External id": 1439023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853890350.036, "dur": 6.083, + "args": { + "External id": 1439024,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890354.980, "dur": 0.909, + "args": { + "External id": 1439025,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853890360.123, "dur": 48.698, + "args": { + "External id": 1439026,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853890361.426, "dur": 46.801, + "args": { + "External id": 1439027,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890414.156, "dur": 17.916, + "args": { + "External id": 1439028,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853890439.365, "dur": 3.926, + "args": { + "External id": 1439029,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890441.689, "dur": 0.600, + "args": { + "External id": 1439030,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853890450.427, "dur": 51.926, + "args": { + "External id": 1439031,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853890451.592, "dur": 3.990, + "args": { + "External id": 1439032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853890452.561, "dur": 2.354, + "args": { + "External id": 1439033,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890454.138, "dur": 0.585, + "args": { + "External id": 1439034,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853890456.243, "dur": 45.574, + "args": { + "External id": 1439035,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853890459.754, "dur": 41.549, + "args": { + "External id": 1439036,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853890507.191, "dur": 6.438, + "args": { + "External id": 1439037,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890509.550, "dur": 2.902, + "args": { + "External id": 1439038,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853890523.407, "dur": 1.929, + "args": { + "External id": 1439039,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853890534.782, "dur": 7.096, + "args": { + "External id": 1439040,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853890537.526, "dur": 4.048, + "args": { + "External id": 1439041,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853890642.863, "dur": 203.553, + "args": { + "External id": 1439042,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853890645.605, "dur": 1.774, + "args": { + "External id": 1439043,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853890651.189, "dur": 194.628, + "args": { + "External id": 1439044,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853890652.814, "dur": 0.654, + "args": { + "External id": 1439045,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853890654.739, "dur": 24.978, + "args": { + "External id": 1439046,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853890681.704, "dur": 4.758, + "args": { + "External id": 1439047,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890685.225, "dur": 0.947, + "args": { + "External id": 1439048,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853890687.381, "dur": 25.313, + "args": { + "External id": 1439049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853890689.000, "dur": 1.537, + "args": { + "External id": 1439050,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853890692.090, "dur": 20.144, + "args": { + "External id": 1439051,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890695.426, "dur": 2.849, + "args": { + "External id": 1439052,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853890714.283, "dur": 24.329, + "args": { + "External id": 1439053,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890740.124, "dur": 16.548, + "args": { + "External id": 1439054,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853890759.620, "dur": 15.936, + "args": { + "External id": 1439055,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890777.146, "dur": 14.290, + "args": { + "External id": 1439056,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853890793.726, "dur": 22.242, + "args": { + "External id": 1439057,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890796.193, "dur": 1.636, + "args": { + "External id": 1439058,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890800.645, "dur": 0.723, + "args": { + "External id": 1439059,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890817.546, "dur": 12.594, + "args": { + "External id": 1439060,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853890831.540, "dur": 12.966, + "args": { + "External id": 1439061,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853890853.333, "dur": 1.862, + "args": { + "External id": 1439062,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853890864.862, "dur": 4.411, + "args": { + "External id": 1439063,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853890867.700, "dur": 0.767, + "args": { + "External id": 1439064,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853890944.189, "dur": 79.194, + "args": { + "External id": 1439065,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853891031.613, "dur": 6.684, + "args": { + "External id": 1439066,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891035.321, "dur": 1.263, + "args": { + "External id": 1439067,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891040.175, "dur": 69.148, + "args": { + "External id": 1439068,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853891118.347, "dur": 28.609, + "args": { + "External id": 1439069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853891120.169, "dur": 25.627, + "args": { + "External id": 1439070,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891144.113, "dur": 1.276, + "args": { + "External id": 1439071,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853891150.997, "dur": 56.262, + "args": { + "External id": 1439072,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853891152.901, "dur": 53.412, + "args": { + "External id": 1439073,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891214.359, "dur": 21.038, + "args": { + "External id": 1439074,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853891243.417, "dur": 7.013, + "args": { + "External id": 1439075,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891248.642, "dur": 0.648, + "args": { + "External id": 1439076,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853891255.170, "dur": 52.664, + "args": { + "External id": 1439077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853891256.328, "dur": 7.185, + "args": { + "External id": 1439078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853891257.489, "dur": 5.353, + "args": { + "External id": 1439079,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891261.872, "dur": 0.803, + "args": { + "External id": 1439080,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853891264.191, "dur": 43.177, + "args": { + "External id": 1439081,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853891264.748, "dur": 41.948, + "args": { + "External id": 1439082,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853891312.493, "dur": 6.858, + "args": { + "External id": 1439083,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891314.925, "dur": 3.112, + "args": { + "External id": 1439084,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853891327.897, "dur": 1.863, + "args": { + "External id": 1439085,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853891338.944, "dur": 9.240, + "args": { + "External id": 1439086,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853891343.524, "dur": 4.403, + "args": { + "External id": 1439087,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853891455.932, "dur": 222.926, + "args": { + "External id": 1439088,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853891458.631, "dur": 2.041, + "args": { + "External id": 1439089,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853891462.107, "dur": 216.110, + "args": { + "External id": 1439090,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853891463.662, "dur": 0.472, + "args": { + "External id": 1439091,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853891465.853, "dur": 27.920, + "args": { + "External id": 1439092,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853891495.675, "dur": 4.817, + "args": { + "External id": 1439093,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891499.108, "dur": 1.023, + "args": { + "External id": 1439094,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853891501.687, "dur": 31.515, + "args": { + "External id": 1439095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853891503.065, "dur": 1.643, + "args": { + "External id": 1439096,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853891506.666, "dur": 26.167, + "args": { + "External id": 1439097,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891510.846, "dur": 3.061, + "args": { + "External id": 1439098,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853891534.798, "dur": 28.267, + "args": { + "External id": 1439099,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891564.976, "dur": 16.827, + "args": { + "External id": 1439100,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853891585.196, "dur": 16.606, + "args": { + "External id": 1439101,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891603.460, "dur": 16.336, + "args": { + "External id": 1439102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853891621.941, "dur": 23.813, + "args": { + "External id": 1439103,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891624.627, "dur": 1.913, + "args": { + "External id": 1439104,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891628.684, "dur": 0.681, + "args": { + "External id": 1439105,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891647.343, "dur": 14.071, + "args": { + "External id": 1439106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891664.292, "dur": 12.779, + "args": { + "External id": 1439107,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853891686.635, "dur": 1.812, + "args": { + "External id": 1439108,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853891698.727, "dur": 4.164, + "args": { + "External id": 1439109,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891701.312, "dur": 0.690, + "args": { + "External id": 1439110,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853891779.029, "dur": 61.196, + "args": { + "External id": 1439111,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853891845.465, "dur": 6.113, + "args": { + "External id": 1439112,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891849.585, "dur": 0.836, + "args": { + "External id": 1439113,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891853.375, "dur": 28.778, + "args": { + "External id": 1439114,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853891889.625, "dur": 5.337, + "args": { + "External id": 1439115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853891891.137, "dur": 3.069, + "args": { + "External id": 1439116,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891893.129, "dur": 0.836, + "args": { + "External id": 1439117,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853891897.989, "dur": 47.638, + "args": { + "External id": 1439118,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853891899.247, "dur": 45.546, + "args": { + "External id": 1439119,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853891950.238, "dur": 17.065, + "args": { + "External id": 1439120,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853891974.078, "dur": 26.986, + "args": { + "External id": 1439121,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853891998.236, "dur": 1.050, + "args": { + "External id": 1439122,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853892007.581, "dur": 97.689, + "args": { + "External id": 1439123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853892008.771, "dur": 4.770, + "args": { + "External id": 1439124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853892010.013, "dur": 2.850, + "args": { + "External id": 1439125,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892011.745, "dur": 0.954, + "args": { + "External id": 1439126,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853892014.249, "dur": 90.401, + "args": { + "External id": 1439127,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853892017.543, "dur": 85.766, + "args": { + "External id": 1439128,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892113.338, "dur": 8.167, + "args": { + "External id": 1439129,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892116.886, "dur": 3.097, + "args": { + "External id": 1439130,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853892129.533, "dur": 2.260, + "args": { + "External id": 1439131,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853892141.027, "dur": 7.921, + "args": { + "External id": 1439132,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853892143.525, "dur": 5.106, + "args": { + "External id": 1439133,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853892256.430, "dur": 211.482, + "args": { + "External id": 1439134,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853892259.332, "dur": 2.386, + "args": { + "External id": 1439135,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853892263.428, "dur": 203.987, + "args": { + "External id": 1439136,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853892265.112, "dur": 0.655, + "args": { + "External id": 1439137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853892267.124, "dur": 26.396, + "args": { + "External id": 1439138,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853892295.562, "dur": 7.350, + "args": { + "External id": 1439139,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892301.833, "dur": 0.795, + "args": { + "External id": 1439140,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853892304.108, "dur": 25.288, + "args": { + "External id": 1439141,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853892306.033, "dur": 1.373, + "args": { + "External id": 1439142,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853892309.149, "dur": 19.773, + "args": { + "External id": 1439143,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892312.771, "dur": 2.792, + "args": { + "External id": 1439144,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853892331.043, "dur": 25.851, + "args": { + "External id": 1439145,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892358.717, "dur": 16.083, + "args": { + "External id": 1439146,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853892377.692, "dur": 15.580, + "args": { + "External id": 1439147,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892394.999, "dur": 14.784, + "args": { + "External id": 1439148,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853892411.924, "dur": 23.983, + "args": { + "External id": 1439149,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892414.479, "dur": 1.597, + "args": { + "External id": 1439150,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892418.523, "dur": 0.785, + "args": { + "External id": 1439151,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892437.514, "dur": 14.280, + "args": { + "External id": 1439152,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892453.184, "dur": 13.063, + "args": { + "External id": 1439153,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853892475.492, "dur": 1.931, + "args": { + "External id": 1439154,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892487.083, "dur": 4.136, + "args": { + "External id": 1439155,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892489.766, "dur": 0.562, + "args": { + "External id": 1439156,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853892568.728, "dur": 61.528, + "args": { + "External id": 1439157,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892636.122, "dur": 5.688, + "args": { + "External id": 1439158,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892639.763, "dur": 0.910, + "args": { + "External id": 1439159,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892643.519, "dur": 28.089, + "args": { + "External id": 1439160,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853892676.786, "dur": 6.683, + "args": { + "External id": 1439161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853892678.809, "dur": 3.930, + "args": { + "External id": 1439162,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892681.720, "dur": 0.747, + "args": { + "External id": 1439163,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853892689.057, "dur": 47.762, + "args": { + "External id": 1439164,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853892690.449, "dur": 45.610, + "args": { + "External id": 1439165,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892741.376, "dur": 17.049, + "args": { + "External id": 1439166,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853892764.230, "dur": 26.609, + "args": { + "External id": 1439167,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853892766.960, "dur": 23.466, + "args": { + "External id": 1439168,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892772.141, "dur": 0.627, + "args": { + "External id": 1439169,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853892796.485, "dur": 32.534, + "args": { + "External id": 1439170,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853892798.674, "dur": 30.107, + "args": { + "External id": 1439171,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 19463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892805.414, "dur": 4.478, + "args": { + "External id": 1439172,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892811.099, "dur": 17.045, + "args": { + "External id": 1439173,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853892844.803, "dur": 5.912, + "args": { + "External id": 1439174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853892847.051, "dur": 3.391, + "args": { + "External id": 1439175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853892852.147, "dur": 1.372, + "args": { + "External id": 1439176,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853892852.880, "dur": 0.546, + "args": { + "External id": 1439177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853892900.287, "dur": 25.622, + "args": { + "External id": 1439178,"Sequence number": 15349088, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 19470 + } + }, + { + "ph": "s", "id": 247, "pid": 2338706, "tid": 2338706, "ts": 6413853892900.287, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892932.870, "dur": 6.942, + "args": { + "External id": 1439179,"Sequence number": 15349089, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 19471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892937.023, "dur": 1.118, + "args": { + "External id": 1439180,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853892942.848, "dur": 9.263, + "args": { + "External id": 1439181,"Sequence number": 15349089, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "1"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 19473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892950.378, "dur": 0.637, + "args": { + "External id": 1439182,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892953.555, "dur": 3.145, + "args": { + "External id": 1439183,"Sequence number": 15349089, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 19475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892955.489, "dur": 0.569, + "args": { + "External id": 1439184,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 19476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892961.733, "dur": 6.872, + "args": { + "External id": 1439185,"Sequence number": 15349089, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19477 + } + }, + { + "ph": "s", "id": 246, "pid": 2338706, "tid": 2338706, "ts": 6413853892961.733, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892966.259, "dur": 0.740, + "args": { + "External id": 1439186,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853892969.881, "dur": 26.815, + "args": { + "External id": 1439187,"Sequence number": 15349090, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19479 + } + }, + { + "ph": "s", "id": 245, "pid": 2338706, "tid": 2338706, "ts": 6413853892969.881, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853892975.391, "dur": 0.514, + "args": { + "External id": 1439188,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853892999.429, "dur": 7.892, + "args": { + "External id": 1439189,"Sequence number": 15349091, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 19481 + } + }, + { + "ph": "s", "id": 244, "pid": 2338706, "tid": 2338706, "ts": 6413853892999.429, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853893004.616, "dur": 1.035, + "args": { + "External id": 1439190,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853893009.041, "dur": 7.825, + "args": { + "External id": 1439191,"Sequence number": 15349092, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 19483 + } + }, + { + "ph": "s", "id": 243, "pid": 2338706, "tid": 2338706, "ts": 6413853893009.041, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853893012.830, "dur": 2.985, + "args": { + "External id": 1439192,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 19484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853893022.509, "dur": 77.986, + "args": { + "External id": 1439193,"Sequence number": 15349093, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853893024.376, "dur": 75.827, + "args": { + "External id": 1439194,"Sequence number": 15349093, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853893027.352, "dur": 10.071, + "args": { + "External id": 1439195,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 19487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853893031.818, "dur": 4.967, + "args": { + "External id": 1439196,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893038.587, "dur": 60.788, + "args": { + "External id": 1439197,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 19489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853893134.543, "dur": 5.861, + "args": { + "External id": 1439198,"Sequence number": 15349093, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 19490 + } + }, + { + "ph": "s", "id": 242, "pid": 2338706, "tid": 2338706, "ts": 6413853893134.543, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853893143.144, "dur": 1.225, + "args": { + "External id": 1439199,"Sequence number": 15349094, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853893183.974, "dur": 44480.578, + "args": { + "External id": 1439200,"Sequence number": 15349094, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 19492 + } + }, + { + "ph": "s", "id": 241, "pid": 2338706, "tid": 2338706, "ts": 6413853893183.974, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853893202.214, "dur": 38.026, + "args": { + "External id": 1439201,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853893203.556, "dur": 36.446, + "args": { + "External id": 1439202,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853893205.356, "dur": 7.086, + "args": { + "External id": 1439203,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853893207.319, "dur": 4.708, + "args": { + "External id": 1439204,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893213.224, "dur": 26.393, + "args": { + "External id": 1439205,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 19497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853893259.680, "dur": 28.495, + "args": { + "External id": 1439206,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853893261.269, "dur": 6.573, + "args": { + "External id": 1439207,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853893263.802, "dur": 3.639, + "args": { + "External id": 1439208,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893269.501, "dur": 18.416, + "args": { + "External id": 1439209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893271.522, "dur": 15.913, + "args": { + "External id": 1439210,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853893292.553, "dur": 24.410, + "args": { + "External id": 1439211,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853893293.554, "dur": 7.682, + "args": { + "External id": 1439212,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853893297.309, "dur": 3.574, + "args": { + "External id": 1439213,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893302.148, "dur": 14.594, + "args": { + "External id": 1439214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893303.017, "dur": 13.286, + "args": { + "External id": 1439215,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 19507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853893323.693, "dur": 21.256, + "args": { + "External id": 1439216,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853893325.571, "dur": 2.641, + "args": { + "External id": 1439217,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893328.981, "dur": 15.659, + "args": { + "External id": 1439218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 19510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893330.051, "dur": 14.238, + "args": { + "External id": 1439219,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413853893350.400, "dur": 32.895, + "args": { + "External id": 1439220,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853893388.559, "dur": 81.171, + "args": { + "External id": 1439221,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853893390.871, "dur": 78.329, + "args": { + "External id": 1439222,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853893395.790, "dur": 1.321, + "args": { + "External id": 1439223,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853893398.708, "dur": 27.678, + "args": { + "External id": 1439224,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853893400.575, "dur": 25.591, + "args": { + "External id": 1439225,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 19517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853893403.395, "dur": 3.657, + "args": { + "External id": 1439226,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853893407.975, "dur": 17.662, + "args": { + "External id": 1439227,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 19519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413853893474.853, "dur": 37245.979, + "args": { + "External id": 1439228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413853893476.580, "dur": 37241.409, + "args": { + "External id": 1439229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853930739.299, "dur": 11.617, + "args": { + "External id": 1439230,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853930746.386, "dur": 2.039, + "args": { + "External id": 1439231,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853930757.470, "dur": 253.275, + "args": { + "External id": 1439232,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853930840.767, "dur": 13.366, + "args": { + "External id": 1439233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853930845.649, "dur": 7.258, + "args": { + "External id": 1439234,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853930851.497, "dur": 1.046, + "args": { + "External id": 1439235,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853930856.869, "dur": 151.799, + "args": { + "External id": 1439236,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853930858.834, "dur": 148.058, + "args": { + "External id": 1439237,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853931019.361, "dur": 9.458, + "args": { + "External id": 1439238,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931024.531, "dur": 0.906, + "args": { + "External id": 1439239,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853931041.831, "dur": 4.294, + "args": { + "External id": 1439240,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853931093.133, "dur": 13.025, + "args": { + "External id": 1439241,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853931096.830, "dur": 8.808, + "args": { + "External id": 1439242,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853931294.505, "dur": 283.967, + "args": { + "External id": 1439243,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853931299.023, "dur": 5.597, + "args": { + "External id": 1439244,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853931306.693, "dur": 270.111, + "args": { + "External id": 1439245,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853931309.982, "dur": 0.537, + "args": { + "External id": 1439246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853931311.947, "dur": 38.673, + "args": { + "External id": 1439247,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853931354.794, "dur": 6.691, + "args": { + "External id": 1439248,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931359.753, "dur": 1.183, + "args": { + "External id": 1439249,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853931363.740, "dur": 36.641, + "args": { + "External id": 1439250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853931365.975, "dur": 1.395, + "args": { + "External id": 1439251,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853931369.152, "dur": 30.033, + "args": { + "External id": 1439252,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931374.744, "dur": 4.897, + "args": { + "External id": 1439253,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853931402.732, "dur": 30.169, + "args": { + "External id": 1439254,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931436.061, "dur": 19.961, + "args": { + "External id": 1439255,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853931461.268, "dur": 23.699, + "args": { + "External id": 1439256,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931487.916, "dur": 18.236, + "args": { + "External id": 1439257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853931509.980, "dur": 29.800, + "args": { + "External id": 1439258,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931513.236, "dur": 3.104, + "args": { + "External id": 1439259,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931519.338, "dur": 1.007, + "args": { + "External id": 1439260,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931542.825, "dur": 15.666, + "args": { + "External id": 1439261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931560.256, "dur": 15.367, + "args": { + "External id": 1439262,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853931588.700, "dur": 2.883, + "args": { + "External id": 1439263,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853931602.015, "dur": 6.546, + "args": { + "External id": 1439264,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931606.416, "dur": 0.783, + "args": { + "External id": 1439265,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853931711.537, "dur": 94.003, + "args": { + "External id": 1439266,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853931814.070, "dur": 9.556, + "args": { + "External id": 1439267,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931818.770, "dur": 0.921, + "args": { + "External id": 1439268,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931825.758, "dur": 35.214, + "args": { + "External id": 1439269,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853931871.500, "dur": 12.812, + "args": { + "External id": 1439270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853931875.013, "dur": 8.425, + "args": { + "External id": 1439271,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931880.014, "dur": 3.078, + "args": { + "External id": 1439272,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853931888.278, "dur": 55.057, + "args": { + "External id": 1439273,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853931889.912, "dur": 52.491, + "args": { + "External id": 1439274,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853931948.599, "dur": 18.374, + "args": { + "External id": 1439275,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853931974.312, "dur": 26.316, + "args": { + "External id": 1439276,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853931996.394, "dur": 1.244, + "args": { + "External id": 1439277,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853932010.780, "dur": 100.481, + "args": { + "External id": 1439278,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853932011.969, "dur": 5.682, + "args": { + "External id": 1439279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853932014.325, "dur": 2.582, + "args": { + "External id": 1439280,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932016.212, "dur": 0.513, + "args": { + "External id": 1439281,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853932018.798, "dur": 91.762, + "args": { + "External id": 1439282,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853932019.747, "dur": 89.352, + "args": { + "External id": 1439283,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853932120.006, "dur": 6.899, + "args": { + "External id": 1439284,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932124.339, "dur": 0.769, + "args": { + "External id": 1439285,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853932137.922, "dur": 2.359, + "args": { + "External id": 1439286,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853932152.154, "dur": 9.471, + "args": { + "External id": 1439287,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853932155.861, "dur": 5.367, + "args": { + "External id": 1439288,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853932286.716, "dur": 233.830, + "args": { + "External id": 1439289,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853932290.782, "dur": 2.595, + "args": { + "External id": 1439290,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853932297.662, "dur": 222.389, + "args": { + "External id": 1439291,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853932299.253, "dur": 0.489, + "args": { + "External id": 1439292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853932301.614, "dur": 28.571, + "args": { + "External id": 1439293,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853932332.252, "dur": 4.588, + "args": { + "External id": 1439294,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932335.515, "dur": 1.010, + "args": { + "External id": 1439295,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853932338.101, "dur": 28.335, + "args": { + "External id": 1439296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853932339.615, "dur": 3.544, + "args": { + "External id": 1439297,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853932344.966, "dur": 21.106, + "args": { + "External id": 1439298,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932348.865, "dur": 2.664, + "args": { + "External id": 1439299,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853932368.458, "dur": 25.128, + "args": { + "External id": 1439300,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932395.494, "dur": 18.681, + "args": { + "External id": 1439301,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853932417.110, "dur": 16.680, + "args": { + "External id": 1439302,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932435.740, "dur": 16.936, + "args": { + "External id": 1439303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853932455.172, "dur": 31.374, + "args": { + "External id": 1439304,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932458.141, "dur": 2.324, + "args": { + "External id": 1439305,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932463.128, "dur": 0.755, + "args": { + "External id": 1439306,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932488.451, "dur": 15.750, + "args": { + "External id": 1439307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932505.548, "dur": 13.081, + "args": { + "External id": 1439308,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853932528.065, "dur": 2.029, + "args": { + "External id": 1439309,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853932541.682, "dur": 5.788, + "args": { + "External id": 1439310,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932545.822, "dur": 0.668, + "args": { + "External id": 1439311,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853932630.232, "dur": 72.618, + "args": { + "External id": 1439312,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853932708.904, "dur": 6.749, + "args": { + "External id": 1439313,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932712.529, "dur": 1.176, + "args": { + "External id": 1439314,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932717.335, "dur": 35.278, + "args": { + "External id": 1439315,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853932758.741, "dur": 7.309, + "args": { + "External id": 1439316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853932760.925, "dur": 4.354, + "args": { + "External id": 1439317,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932764.164, "dur": 0.859, + "args": { + "External id": 1439318,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853932769.188, "dur": 51.589, + "args": { + "External id": 1439319,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853932770.575, "dur": 49.543, + "args": { + "External id": 1439320,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853932825.621, "dur": 18.164, + "args": { + "External id": 1439321,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853932850.261, "dur": 6.186, + "args": { + "External id": 1439322,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932854.918, "dur": 0.493, + "args": { + "External id": 1439323,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853932861.417, "dur": 83.233, + "args": { + "External id": 1439324,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853932862.460, "dur": 6.164, + "args": { + "External id": 1439325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853932863.309, "dur": 4.625, + "args": { + "External id": 1439326,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932867.101, "dur": 0.665, + "args": { + "External id": 1439327,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853932869.346, "dur": 74.820, + "args": { + "External id": 1439328,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853932869.926, "dur": 73.567, + "args": { + "External id": 1439329,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853932951.421, "dur": 7.409, + "args": { + "External id": 1439330,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853932953.766, "dur": 3.895, + "args": { + "External id": 1439331,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853932965.918, "dur": 1.531, + "args": { + "External id": 1439332,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853932976.285, "dur": 30.794, + "args": { + "External id": 1439333,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853932999.798, "dur": 6.748, + "args": { + "External id": 1439334,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853933168.575, "dur": 229.941, + "args": { + "External id": 1439335,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853933172.440, "dur": 3.870, + "args": { + "External id": 1439336,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853933178.588, "dur": 219.257, + "args": { + "External id": 1439337,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853933180.371, "dur": 0.445, + "args": { + "External id": 1439338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853933182.678, "dur": 29.993, + "args": { + "External id": 1439339,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853933215.002, "dur": 4.675, + "args": { + "External id": 1439340,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933218.326, "dur": 0.945, + "args": { + "External id": 1439341,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853933221.040, "dur": 28.543, + "args": { + "External id": 1439342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853933222.770, "dur": 1.435, + "args": { + "External id": 1439343,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853933226.026, "dur": 23.185, + "args": { + "External id": 1439344,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933229.822, "dur": 3.424, + "args": { + "External id": 1439345,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853933251.544, "dur": 28.141, + "args": { + "External id": 1439346,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933281.771, "dur": 18.977, + "args": { + "External id": 1439347,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853933304.642, "dur": 18.889, + "args": { + "External id": 1439348,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933325.219, "dur": 15.464, + "args": { + "External id": 1439349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853933342.919, "dur": 23.410, + "args": { + "External id": 1439350,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933345.945, "dur": 1.812, + "args": { + "External id": 1439351,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933350.078, "dur": 0.923, + "args": { + "External id": 1439352,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933367.815, "dur": 14.452, + "args": { + "External id": 1439353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933383.559, "dur": 13.164, + "args": { + "External id": 1439354,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853933407.558, "dur": 2.505, + "args": { + "External id": 1439355,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853933421.662, "dur": 5.921, + "args": { + "External id": 1439356,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933424.853, "dur": 1.596, + "args": { + "External id": 1439357,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853933509.159, "dur": 71.128, + "args": { + "External id": 1439358,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853933586.147, "dur": 5.579, + "args": { + "External id": 1439359,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933589.661, "dur": 0.644, + "args": { + "External id": 1439360,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933594.019, "dur": 30.397, + "args": { + "External id": 1439361,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853933630.013, "dur": 5.784, + "args": { + "External id": 1439362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853933631.714, "dur": 3.214, + "args": { + "External id": 1439363,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933633.787, "dur": 0.917, + "args": { + "External id": 1439364,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853933639.087, "dur": 48.726, + "args": { + "External id": 1439365,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853933640.244, "dur": 46.827, + "args": { + "External id": 1439366,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933693.081, "dur": 18.080, + "args": { + "External id": 1439367,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853933717.776, "dur": 4.595, + "args": { + "External id": 1439368,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933720.754, "dur": 0.554, + "args": { + "External id": 1439369,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853933727.051, "dur": 52.165, + "args": { + "External id": 1439370,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853933728.175, "dur": 6.007, + "args": { + "External id": 1439371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853933729.029, "dur": 4.473, + "args": { + "External id": 1439372,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933732.754, "dur": 0.584, + "args": { + "External id": 1439373,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853933735.002, "dur": 43.825, + "args": { + "External id": 1439374,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853933735.658, "dur": 42.371, + "args": { + "External id": 1439375,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853933784.342, "dur": 4.281, + "args": { + "External id": 1439376,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933786.691, "dur": 0.773, + "args": { + "External id": 1439377,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853933795.163, "dur": 1.579, + "args": { + "External id": 1439378,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853933805.329, "dur": 8.036, + "args": { + "External id": 1439379,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853933809.534, "dur": 3.532, + "args": { + "External id": 1439380,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853933911.111, "dur": 271.952, + "args": { + "External id": 1439381,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853933913.091, "dur": 4.816, + "args": { + "External id": 1439382,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853933919.764, "dur": 262.632, + "args": { + "External id": 1439383,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853933921.027, "dur": 0.388, + "args": { + "External id": 1439384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853933923.204, "dur": 23.442, + "args": { + "External id": 1439385,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853933948.830, "dur": 3.486, + "args": { + "External id": 1439386,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853933951.282, "dur": 0.759, + "args": { + "External id": 1439387,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853933953.563, "dur": 40.073, + "args": { + "External id": 1439388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853933955.205, "dur": 1.433, + "args": { + "External id": 1439389,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853933958.109, "dur": 18.261, + "args": { + "External id": 1439390,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853933961.327, "dur": 2.057, + "args": { + "External id": 1439391,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853933997.802, "dur": 25.085, + "args": { + "External id": 1439392,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934024.711, "dur": 16.575, + "args": { + "External id": 1439393,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853934044.268, "dur": 53.491, + "args": { + "External id": 1439394,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934103.827, "dur": 17.054, + "args": { + "External id": 1439395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853934123.609, "dur": 26.513, + "args": { + "External id": 1439396,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934126.434, "dur": 2.671, + "args": { + "External id": 1439397,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934131.852, "dur": 0.885, + "args": { + "External id": 1439398,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934151.987, "dur": 14.292, + "args": { + "External id": 1439399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934167.392, "dur": 13.531, + "args": { + "External id": 1439400,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853934192.626, "dur": 2.593, + "args": { + "External id": 1439401,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853934206.837, "dur": 4.860, + "args": { + "External id": 1439402,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934210.071, "dur": 0.646, + "args": { + "External id": 1439403,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853934298.032, "dur": 68.340, + "args": { + "External id": 1439404,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853934372.665, "dur": 8.018, + "args": { + "External id": 1439405,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934378.505, "dur": 0.884, + "args": { + "External id": 1439406,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934382.322, "dur": 29.801, + "args": { + "External id": 1439407,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853934417.691, "dur": 6.097, + "args": { + "External id": 1439408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853934419.441, "dur": 3.513, + "args": { + "External id": 1439409,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934421.897, "dur": 0.844, + "args": { + "External id": 1439410,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853934427.128, "dur": 57.295, + "args": { + "External id": 1439411,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853934430.616, "dur": 52.839, + "args": { + "External id": 1439412,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934489.288, "dur": 18.363, + "args": { + "External id": 1439413,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853934514.570, "dur": 4.373, + "args": { + "External id": 1439414,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934517.165, "dur": 0.713, + "args": { + "External id": 1439415,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853934523.842, "dur": 53.318, + "args": { + "External id": 1439416,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853934525.060, "dur": 6.645, + "args": { + "External id": 1439417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853934525.933, "dur": 5.145, + "args": { + "External id": 1439418,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934530.090, "dur": 0.831, + "args": { + "External id": 1439419,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853934532.309, "dur": 44.340, + "args": { + "External id": 1439420,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853934533.387, "dur": 42.670, + "args": { + "External id": 1439421,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853934581.919, "dur": 4.109, + "args": { + "External id": 1439422,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934584.214, "dur": 0.575, + "args": { + "External id": 1439423,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853934593.183, "dur": 1.721, + "args": { + "External id": 1439424,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853934606.596, "dur": 9.127, + "args": { + "External id": 1439425,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853934609.142, "dur": 6.288, + "args": { + "External id": 1439426,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853934720.582, "dur": 206.657, + "args": { + "External id": 1439427,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853934723.185, "dur": 2.411, + "args": { + "External id": 1439428,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853934727.032, "dur": 199.706, + "args": { + "External id": 1439429,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853934728.388, "dur": 0.469, + "args": { + "External id": 1439430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853934730.624, "dur": 24.221, + "args": { + "External id": 1439431,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853934756.974, "dur": 4.583, + "args": { + "External id": 1439432,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934760.223, "dur": 0.968, + "args": { + "External id": 1439433,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853934762.471, "dur": 28.752, + "args": { + "External id": 1439434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853934764.006, "dur": 1.405, + "args": { + "External id": 1439435,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853934767.306, "dur": 23.385, + "args": { + "External id": 1439436,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934773.062, "dur": 3.575, + "args": { + "External id": 1439437,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853934792.697, "dur": 21.461, + "args": { + "External id": 1439438,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934815.950, "dur": 17.199, + "args": { + "External id": 1439439,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853934836.483, "dur": 17.582, + "args": { + "External id": 1439440,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934855.514, "dur": 16.396, + "args": { + "External id": 1439441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853934874.374, "dur": 23.785, + "args": { + "External id": 1439442,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934876.774, "dur": 1.571, + "args": { + "External id": 1439443,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934880.904, "dur": 0.808, + "args": { + "External id": 1439444,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934899.398, "dur": 13.305, + "args": { + "External id": 1439445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853934914.092, "dur": 11.600, + "args": { + "External id": 1439446,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853934934.455, "dur": 1.914, + "args": { + "External id": 1439447,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853934945.828, "dur": 4.760, + "args": { + "External id": 1439448,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853934949.043, "dur": 0.624, + "args": { + "External id": 1439449,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853935054.725, "dur": 107.704, + "args": { + "External id": 1439450,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853935170.949, "dur": 7.624, + "args": { + "External id": 1439451,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935175.698, "dur": 1.009, + "args": { + "External id": 1439452,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935180.443, "dur": 29.825, + "args": { + "External id": 1439453,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853935216.195, "dur": 6.587, + "args": { + "External id": 1439454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853935218.040, "dur": 3.950, + "args": { + "External id": 1439455,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935221.022, "dur": 0.731, + "args": { + "External id": 1439456,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853935226.608, "dur": 46.465, + "args": { + "External id": 1439457,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853935228.012, "dur": 44.264, + "args": { + "External id": 1439458,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935277.904, "dur": 18.652, + "args": { + "External id": 1439459,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853935303.536, "dur": 6.811, + "args": { + "External id": 1439460,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935308.776, "dur": 0.598, + "args": { + "External id": 1439461,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853935315.203, "dur": 53.678, + "args": { + "External id": 1439462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853935316.175, "dur": 7.005, + "args": { + "External id": 1439463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853935317.176, "dur": 5.330, + "args": { + "External id": 1439464,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935318.853, "dur": 3.501, + "args": { + "External id": 1439465,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853935323.776, "dur": 44.700, + "args": { + "External id": 1439466,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853935326.688, "dur": 40.965, + "args": { + "External id": 1439467,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853935374.075, "dur": 4.248, + "args": { + "External id": 1439468,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935376.609, "dur": 0.535, + "args": { + "External id": 1439469,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853935385.909, "dur": 2.244, + "args": { + "External id": 1439470,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853935397.694, "dur": 7.368, + "args": { + "External id": 1439471,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853935400.231, "dur": 4.505, + "args": { + "External id": 1439472,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853935511.696, "dur": 205.665, + "args": { + "External id": 1439473,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853935514.340, "dur": 1.896, + "args": { + "External id": 1439474,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853935517.684, "dur": 199.093, + "args": { + "External id": 1439475,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853935519.055, "dur": 0.460, + "args": { + "External id": 1439476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853935520.753, "dur": 24.315, + "args": { + "External id": 1439477,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853935547.331, "dur": 4.206, + "args": { + "External id": 1439478,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935550.497, "dur": 0.731, + "args": { + "External id": 1439479,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853935552.478, "dur": 25.615, + "args": { + "External id": 1439480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853935554.228, "dur": 1.390, + "args": { + "External id": 1439481,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853935557.130, "dur": 20.522, + "args": { + "External id": 1439482,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935560.663, "dur": 2.618, + "args": { + "External id": 1439483,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853935579.625, "dur": 25.718, + "args": { + "External id": 1439484,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935607.101, "dur": 17.579, + "args": { + "External id": 1439485,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853935627.600, "dur": 15.043, + "args": { + "External id": 1439486,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935644.382, "dur": 14.883, + "args": { + "External id": 1439487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853935661.359, "dur": 23.166, + "args": { + "External id": 1439488,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935663.899, "dur": 1.913, + "args": { + "External id": 1439489,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935667.619, "dur": 1.037, + "args": { + "External id": 1439490,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935686.539, "dur": 15.178, + "args": { + "External id": 1439491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935702.893, "dur": 12.543, + "args": { + "External id": 1439492,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853935724.912, "dur": 2.005, + "args": { + "External id": 1439493,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853935737.249, "dur": 4.173, + "args": { + "External id": 1439494,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935739.829, "dur": 0.551, + "args": { + "External id": 1439495,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853935813.851, "dur": 55.289, + "args": { + "External id": 1439496,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853935876.695, "dur": 5.455, + "args": { + "External id": 1439497,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935880.124, "dur": 0.743, + "args": { + "External id": 1439498,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935883.625, "dur": 24.664, + "args": { + "External id": 1439499,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853935913.178, "dur": 5.802, + "args": { + "External id": 1439500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853935914.981, "dur": 3.301, + "args": { + "External id": 1439501,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853935917.250, "dur": 0.825, + "args": { + "External id": 1439502,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853935924.081, "dur": 44.214, + "args": { + "External id": 1439503,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853935925.122, "dur": 42.354, + "args": { + "External id": 1439504,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853935972.540, "dur": 36.763, + "args": { + "External id": 1439505,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853936018.352, "dur": 5.957, + "args": { + "External id": 1439506,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936021.919, "dur": 1.150, + "args": { + "External id": 1439507,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853936029.399, "dur": 99.512, + "args": { + "External id": 1439508,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853936030.559, "dur": 5.827, + "args": { + "External id": 1439509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853936033.655, "dur": 2.100, + "args": { + "External id": 1439510,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936035.054, "dur": 0.548, + "args": { + "External id": 1439511,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853936037.161, "dur": 91.289, + "args": { + "External id": 1439512,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853936038.215, "dur": 88.857, + "args": { + "External id": 1439513,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853936137.380, "dur": 10.926, + "args": { + "External id": 1439514,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936144.080, "dur": 2.785, + "args": { + "External id": 1439515,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853936157.443, "dur": 1.994, + "args": { + "External id": 1439516,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936170.965, "dur": 7.363, + "args": { + "External id": 1439517,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936173.030, "dur": 5.013, + "args": { + "External id": 1439518,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853936282.894, "dur": 212.652, + "args": { + "External id": 1439519,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936285.216, "dur": 2.348, + "args": { + "External id": 1439520,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853936289.345, "dur": 205.760, + "args": { + "External id": 1439521,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853936291.044, "dur": 0.541, + "args": { + "External id": 1439522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853936295.247, "dur": 26.842, + "args": { + "External id": 1439523,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853936324.098, "dur": 4.016, + "args": { + "External id": 1439524,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936327.109, "dur": 0.717, + "args": { + "External id": 1439525,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853936329.127, "dur": 27.984, + "args": { + "External id": 1439526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936330.814, "dur": 1.404, + "args": { + "External id": 1439527,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853936334.081, "dur": 22.633, + "args": { + "External id": 1439528,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936337.660, "dur": 3.529, + "args": { + "External id": 1439529,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853936358.762, "dur": 26.454, + "args": { + "External id": 1439530,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936386.919, "dur": 15.840, + "args": { + "External id": 1439531,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853936405.801, "dur": 16.758, + "args": { + "External id": 1439532,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936424.085, "dur": 15.119, + "args": { + "External id": 1439533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853936441.331, "dur": 22.614, + "args": { + "External id": 1439534,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936444.454, "dur": 1.650, + "args": { + "External id": 1439535,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936448.719, "dur": 0.776, + "args": { + "External id": 1439536,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936465.644, "dur": 13.943, + "args": { + "External id": 1439537,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936480.641, "dur": 13.479, + "args": { + "External id": 1439538,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853936502.474, "dur": 1.595, + "args": { + "External id": 1439539,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853936514.274, "dur": 4.498, + "args": { + "External id": 1439540,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936517.223, "dur": 0.569, + "args": { + "External id": 1439541,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853936594.118, "dur": 62.776, + "args": { + "External id": 1439542,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853936662.389, "dur": 5.488, + "args": { + "External id": 1439543,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936665.661, "dur": 0.770, + "args": { + "External id": 1439544,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936669.896, "dur": 28.452, + "args": { + "External id": 1439545,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853936703.724, "dur": 6.816, + "args": { + "External id": 1439546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853936706.120, "dur": 3.653, + "args": { + "External id": 1439547,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936708.820, "dur": 0.768, + "args": { + "External id": 1439548,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853936713.293, "dur": 46.186, + "args": { + "External id": 1439549,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853936714.323, "dur": 44.390, + "args": { + "External id": 1439550,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853936763.960, "dur": 15.465, + "args": { + "External id": 1439551,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853936788.716, "dur": 4.452, + "args": { + "External id": 1439552,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936791.540, "dur": 0.551, + "args": { + "External id": 1439553,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853936797.653, "dur": 48.964, + "args": { + "External id": 1439554,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853936798.749, "dur": 3.490, + "args": { + "External id": 1439555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853936799.525, "dur": 2.101, + "args": { + "External id": 1439556,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936801.028, "dur": 0.439, + "args": { + "External id": 1439557,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853936805.473, "dur": 40.720, + "args": { + "External id": 1439558,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853936805.936, "dur": 39.493, + "args": { + "External id": 1439559,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853936851.419, "dur": 3.940, + "args": { + "External id": 1439560,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853936853.537, "dur": 0.644, + "args": { + "External id": 1439561,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853936861.358, "dur": 1.753, + "args": { + "External id": 1439562,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936870.937, "dur": 8.296, + "args": { + "External id": 1439563,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936875.378, "dur": 3.566, + "args": { + "External id": 1439564,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853936968.422, "dur": 266.511, + "args": { + "External id": 1439565,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853936970.491, "dur": 4.013, + "args": { + "External id": 1439566,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853936975.837, "dur": 258.634, + "args": { + "External id": 1439567,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853936994.697, "dur": 0.508, + "args": { + "External id": 1439568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853936997.142, "dur": 26.824, + "args": { + "External id": 1439569,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853937026.055, "dur": 4.451, + "args": { + "External id": 1439570,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937029.264, "dur": 0.952, + "args": { + "External id": 1439571,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853937031.471, "dur": 59.940, + "args": { + "External id": 1439572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853937032.706, "dur": 1.566, + "args": { + "External id": 1439573,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853937035.722, "dur": 54.635, + "args": { + "External id": 1439574,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937038.962, "dur": 2.027, + "args": { + "External id": 1439575,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853937094.921, "dur": 26.598, + "args": { + "External id": 1439576,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937123.165, "dur": 19.106, + "args": { + "External id": 1439577,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853937145.401, "dur": 16.985, + "args": { + "External id": 1439578,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937163.806, "dur": 15.666, + "args": { + "External id": 1439579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853937181.994, "dur": 23.299, + "args": { + "External id": 1439580,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937184.862, "dur": 2.157, + "args": { + "External id": 1439581,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937189.246, "dur": 0.980, + "args": { + "External id": 1439582,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937206.871, "dur": 13.266, + "args": { + "External id": 1439583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937221.269, "dur": 11.825, + "args": { + "External id": 1439584,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853937245.456, "dur": 2.699, + "args": { + "External id": 1439585,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937259.073, "dur": 5.629, + "args": { + "External id": 1439586,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937261.872, "dur": 0.850, + "args": { + "External id": 1439587,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853937345.451, "dur": 65.967, + "args": { + "External id": 1439588,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937417.499, "dur": 5.760, + "args": { + "External id": 1439589,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937421.025, "dur": 1.010, + "args": { + "External id": 1439590,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937424.993, "dur": 30.173, + "args": { + "External id": 1439591,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853937460.723, "dur": 5.765, + "args": { + "External id": 1439592,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853937462.431, "dur": 3.301, + "args": { + "External id": 1439593,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937464.863, "dur": 0.685, + "args": { + "External id": 1439594,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853937469.489, "dur": 48.185, + "args": { + "External id": 1439595,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853937471.088, "dur": 45.942, + "args": { + "External id": 1439596,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937522.323, "dur": 19.026, + "args": { + "External id": 1439597,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853937546.673, "dur": 28.865, + "args": { + "External id": 1439598,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853937550.151, "dur": 24.955, + "args": { + "External id": 1439599,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937555.638, "dur": 0.918, + "args": { + "External id": 1439600,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853937581.402, "dur": 34.728, + "args": { + "External id": 1439601,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853937583.492, "dur": 32.385, + "args": { + "External id": 1439602,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 19894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937589.307, "dur": 4.329, + "args": { + "External id": 1439603,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937597.103, "dur": 18.226, + "args": { + "External id": 1439604,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853937629.006, "dur": 6.724, + "args": { + "External id": 1439605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853937631.110, "dur": 4.065, + "args": { + "External id": 1439606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853937636.975, "dur": 1.515, + "args": { + "External id": 1439607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853937637.656, "dur": 0.748, + "args": { + "External id": 1439608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937683.056, "dur": 26.778, + "args": { + "External id": 1439609,"Sequence number": 15349095, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 19901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937711.762, "dur": 17.212, + "args": { + "External id": 1439610,"Sequence number": 15349096, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 19902 + } + }, + { + "ph": "s", "id": 240, "pid": 2338706, "tid": 2338706, "ts": 6413853937711.762, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937735.601, "dur": 7.054, + "args": { + "External id": 1439611,"Sequence number": 15349097, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 19903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937739.858, "dur": 1.203, + "args": { + "External id": 1439612,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853937745.500, "dur": 6.569, + "args": { + "External id": 1439613,"Sequence number": 15349097, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 19905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937750.295, "dur": 0.509, + "args": { + "External id": 1439614,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 19906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937753.527, "dur": 5.274, + "args": { + "External id": 1439615,"Sequence number": 15349097, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 19907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937757.722, "dur": 0.329, + "args": { + "External id": 1439616,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 19908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937763.403, "dur": 5.919, + "args": { + "External id": 1439617,"Sequence number": 15349097, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19909 + } + }, + { + "ph": "s", "id": 239, "pid": 2338706, "tid": 2338706, "ts": 6413853937763.403, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937766.818, "dur": 0.960, + "args": { + "External id": 1439618,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937770.539, "dur": 5.437, + "args": { + "External id": 1439619,"Sequence number": 15349098, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 19911 + } + }, + { + "ph": "s", "id": 238, "pid": 2338706, "tid": 2338706, "ts": 6413853937770.539, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937774.456, "dur": 0.531, + "args": { + "External id": 1439620,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853937779.464, "dur": 5.546, + "args": { + "External id": 1439621,"Sequence number": 15349099, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 19913 + } + }, + { + "ph": "s", "id": 237, "pid": 2338706, "tid": 2338706, "ts": 6413853937779.464, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937783.266, "dur": 0.748, + "args": { + "External id": 1439622,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 19914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853937786.391, "dur": 7.566, + "args": { + "External id": 1439623,"Sequence number": 15349100, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 19915 + } + }, + { + "ph": "s", "id": 236, "pid": 2338706, "tid": 2338706, "ts": 6413853937786.391, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853937789.908, "dur": 3.023, + "args": { + "External id": 1439624,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "8192"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 19916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853937798.484, "dur": 37.628, + "args": { + "External id": 1439625,"Sequence number": 15349101, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853937800.405, "dur": 35.467, + "args": { + "External id": 1439626,"Sequence number": 15349101, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853937803.594, "dur": 7.895, + "args": { + "External id": 1439627,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 19919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853937806.526, "dur": 4.363, + "args": { + "External id": 1439628,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937814.855, "dur": 20.408, + "args": { + "External id": 1439629,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 19921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853937864.843, "dur": 4.415, + "args": { + "External id": 1439630,"Sequence number": 15349101, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 19922 + } + }, + { + "ph": "s", "id": 235, "pid": 2338706, "tid": 2338706, "ts": 6413853937864.843, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853937872.022, "dur": 1.186, + "args": { + "External id": 1439631,"Sequence number": 15349102, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 19923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853937910.677, "dur": 44837.145, + "args": { + "External id": 1439632,"Sequence number": 15349102, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 19924 + } + }, + { + "ph": "s", "id": 234, "pid": 2338706, "tid": 2338706, "ts": 6413853937910.677, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853937928.036, "dur": 35.422, + "args": { + "External id": 1439633,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853937933.489, "dur": 29.734, + "args": { + "External id": 1439634,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853937935.267, "dur": 7.439, + "args": { + "External id": 1439635,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853937938.883, "dur": 3.330, + "args": { + "External id": 1439636,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853937943.494, "dur": 19.307, + "args": { + "External id": 1439637,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 19929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853938005.664, "dur": 33.148, + "args": { + "External id": 1439638,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853938006.846, "dur": 8.557, + "args": { + "External id": 1439639,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 19931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853938009.496, "dur": 5.334, + "args": { + "External id": 1439640,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938017.148, "dur": 21.399, + "args": { + "External id": 1439641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 19933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938019.073, "dur": 18.976, + "args": { + "External id": 1439642,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 19934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853938042.955, "dur": 66.416, + "args": { + "External id": 1439643,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853938043.795, "dur": 5.076, + "args": { + "External id": 1439644,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 19936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853938045.484, "dur": 3.085, + "args": { + "External id": 1439645,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938051.977, "dur": 57.155, + "args": { + "External id": 1439646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938052.702, "dur": 55.377, + "args": { + "External id": 1439647,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 19939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853938119.196, "dur": 23.645, + "args": { + "External id": 1439648,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 19940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853938121.247, "dur": 4.506, + "args": { + "External id": 1439649,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938126.579, "dur": 15.897, + "args": { + "External id": 1439650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 19942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938128.008, "dur": 14.023, + "args": { + "External id": 1439651,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413853938148.776, "dur": 29.188, + "args": { + "External id": 1439652,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853938181.406, "dur": 60.629, + "args": { + "External id": 1439653,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 19945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853938186.163, "dur": 55.405, + "args": { + "External id": 1439654,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853938192.047, "dur": 1.074, + "args": { + "External id": 1439655,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 19947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853938194.596, "dur": 28.957, + "args": { + "External id": 1439656,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853938196.668, "dur": 26.551, + "args": { + "External id": 1439657,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 19949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853938199.746, "dur": 2.895, + "args": { + "External id": 1439658,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853938203.656, "dur": 19.148, + "args": { + "External id": 1439659,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 19951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413853938246.556, "dur": 37420.399, + "args": { + "External id": 1439660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413853938248.560, "dur": 37416.547, + "args": { + "External id": 1439661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853975687.031, "dur": 13.684, + "args": { + "External id": 1439662,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853975694.982, "dur": 2.969, + "args": { + "External id": 1439663,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853975711.032, "dur": 139.825, + "args": { + "External id": 1439664,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 19956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853975713.911, "dur": 9.440, + "args": { + "External id": 1439665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 19957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853975716.882, "dur": 4.276, + "args": { + "External id": 1439666,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 19958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853975719.717, "dur": 1.085, + "args": { + "External id": 1439667,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 19959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853975724.923, "dur": 124.895, + "args": { + "External id": 1439668,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853975727.039, "dur": 121.802, + "args": { + "External id": 1439669,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 19961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853975856.664, "dur": 6.262, + "args": { + "External id": 1439670,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853975860.240, "dur": 0.887, + "args": { + "External id": 1439671,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853975878.311, "dur": 4.503, + "args": { + "External id": 1439672,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 19964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853975896.723, "dur": 10.488, + "args": { + "External id": 1439673,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 19965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853975900.671, "dur": 6.200, + "args": { + "External id": 1439674,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853976149.590, "dur": 313.014, + "args": { + "External id": 1439675,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853976154.815, "dur": 5.380, + "args": { + "External id": 1439676,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853976166.353, "dur": 295.457, + "args": { + "External id": 1439677,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 19969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853976168.715, "dur": 1.357, + "args": { + "External id": 1439678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853976171.889, "dur": 39.824, + "args": { + "External id": 1439679,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 19971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853976213.930, "dur": 6.765, + "args": { + "External id": 1439680,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 19972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976218.845, "dur": 1.424, + "args": { + "External id": 1439681,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 19973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853976222.115, "dur": 72.374, + "args": { + "External id": 1439682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853976257.262, "dur": 2.970, + "args": { + "External id": 1439683,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 19975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853976262.270, "dur": 31.840, + "args": { + "External id": 1439684,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 19976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976269.174, "dur": 4.835, + "args": { + "External id": 1439685,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853976297.756, "dur": 30.609, + "args": { + "External id": 1439686,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976330.604, "dur": 21.366, + "args": { + "External id": 1439687,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853976356.923, "dur": 19.436, + "args": { + "External id": 1439688,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 19980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976379.398, "dur": 16.030, + "args": { + "External id": 1439689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 19981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853976397.803, "dur": 26.995, + "args": { + "External id": 1439690,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 19982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976401.386, "dur": 1.597, + "args": { + "External id": 1439691,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 19983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976405.387, "dur": 0.903, + "args": { + "External id": 1439692,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 19984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976426.421, "dur": 16.175, + "args": { + "External id": 1439693,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 19985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976445.811, "dur": 14.850, + "args": { + "External id": 1439694,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 19986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853976472.336, "dur": 3.080, + "args": { + "External id": 1439695,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 19987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853976485.242, "dur": 6.843, + "args": { + "External id": 1439696,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 19988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976489.950, "dur": 0.789, + "args": { + "External id": 1439697,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 19989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853976599.320, "dur": 93.384, + "args": { + "External id": 1439698,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 19990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853976700.032, "dur": 8.840, + "args": { + "External id": 1439699,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 19991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976703.856, "dur": 2.110, + "args": { + "External id": 1439700,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 19992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976710.971, "dur": 35.795, + "args": { + "External id": 1439701,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 19993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853976755.880, "dur": 7.872, + "args": { + "External id": 1439702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 19994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853976759.089, "dur": 3.783, + "args": { + "External id": 1439703,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 19995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976761.517, "dur": 1.049, + "args": { + "External id": 1439704,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 19996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853976767.251, "dur": 60.673, + "args": { + "External id": 1439705,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853976768.925, "dur": 58.201, + "args": { + "External id": 1439706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 19998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853976833.075, "dur": 19.668, + "args": { + "External id": 1439707,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 19999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853976860.486, "dur": 7.557, + "args": { + "External id": 1439708,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976866.356, "dur": 0.582, + "args": { + "External id": 1439709,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853976874.512, "dur": 59.080, + "args": { + "External id": 1439710,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853976875.558, "dur": 5.061, + "args": { + "External id": 1439711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853976876.298, "dur": 3.608, + "args": { + "External id": 1439712,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976877.711, "dur": 2.029, + "args": { + "External id": 1439713,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853976881.580, "dur": 51.522, + "args": { + "External id": 1439714,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853976884.841, "dur": 47.557, + "args": { + "External id": 1439715,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853976938.202, "dur": 4.258, + "args": { + "External id": 1439716,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853976940.693, "dur": 0.399, + "args": { + "External id": 1439717,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853976949.715, "dur": 2.203, + "args": { + "External id": 1439718,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853976961.983, "dur": 11.746, + "args": { + "External id": 1439719,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853976967.919, "dur": 5.501, + "args": { + "External id": 1439720,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853977161.178, "dur": 237.410, + "args": { + "External id": 1439721,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853977165.419, "dur": 4.134, + "args": { + "External id": 1439722,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853977171.638, "dur": 226.419, + "args": { + "External id": 1439723,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853977173.501, "dur": 0.532, + "args": { + "External id": 1439724,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853977175.426, "dur": 29.616, + "args": { + "External id": 1439725,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853977207.363, "dur": 6.638, + "args": { + "External id": 1439726,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977210.292, "dur": 3.337, + "args": { + "External id": 1439727,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853977215.018, "dur": 28.919, + "args": { + "External id": 1439728,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853977216.889, "dur": 1.547, + "args": { + "External id": 1439729,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853977220.249, "dur": 23.246, + "args": { + "External id": 1439730,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977223.993, "dur": 2.809, + "args": { + "External id": 1439731,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853977245.876, "dur": 27.569, + "args": { + "External id": 1439732,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977275.355, "dur": 17.431, + "args": { + "External id": 1439733,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853977295.699, "dur": 18.967, + "args": { + "External id": 1439734,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977316.373, "dur": 16.557, + "args": { + "External id": 1439735,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853977335.300, "dur": 26.293, + "args": { + "External id": 1439736,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977337.964, "dur": 2.706, + "args": { + "External id": 1439737,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977343.172, "dur": 0.825, + "args": { + "External id": 1439738,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977365.725, "dur": 15.087, + "args": { + "External id": 1439739,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977382.000, "dur": 14.649, + "args": { + "External id": 1439740,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853977407.677, "dur": 2.860, + "args": { + "External id": 1439741,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853977423.600, "dur": 6.225, + "args": { + "External id": 1439742,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977428.286, "dur": 0.586, + "args": { + "External id": 1439743,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853977514.756, "dur": 78.613, + "args": { + "External id": 1439744,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853977682.072, "dur": 7.932, + "args": { + "External id": 1439745,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977687.377, "dur": 0.821, + "args": { + "External id": 1439746,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977691.845, "dur": 40.902, + "args": { + "External id": 1439747,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853977742.047, "dur": 8.443, + "args": { + "External id": 1439748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853977743.887, "dur": 5.832, + "args": { + "External id": 1439749,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977748.667, "dur": 0.790, + "args": { + "External id": 1439750,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853977754.167, "dur": 83.767, + "args": { + "External id": 1439751,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853977755.282, "dur": 81.710, + "args": { + "External id": 1439752,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853977844.131, "dur": 21.130, + "args": { + "External id": 1439753,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853977872.286, "dur": 6.624, + "args": { + "External id": 1439754,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977877.303, "dur": 0.603, + "args": { + "External id": 1439755,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853977884.044, "dur": 57.138, + "args": { + "External id": 1439756,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853977884.921, "dur": 4.634, + "args": { + "External id": 1439757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853977885.801, "dur": 3.102, + "args": { + "External id": 1439758,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977887.646, "dur": 0.809, + "args": { + "External id": 1439759,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853977890.295, "dur": 50.516, + "args": { + "External id": 1439760,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853977893.223, "dur": 46.835, + "args": { + "External id": 1439761,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853977946.121, "dur": 6.440, + "args": { + "External id": 1439762,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853977948.222, "dur": 2.927, + "args": { + "External id": 1439763,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853977960.309, "dur": 1.894, + "args": { + "External id": 1439764,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853977972.029, "dur": 27.482, + "args": { + "External id": 1439765,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853977974.683, "dur": 22.905, + "args": { + "External id": 1439766,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853978169.186, "dur": 229.235, + "args": { + "External id": 1439767,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853978172.564, "dur": 3.936, + "args": { + "External id": 1439768,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853978178.388, "dur": 219.456, + "args": { + "External id": 1439769,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853978180.301, "dur": 0.723, + "args": { + "External id": 1439770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853978182.658, "dur": 29.625, + "args": { + "External id": 1439771,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853978214.293, "dur": 4.480, + "args": { + "External id": 1439772,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978217.321, "dur": 1.116, + "args": { + "External id": 1439773,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853978220.004, "dur": 27.127, + "args": { + "External id": 1439774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853978221.411, "dur": 1.367, + "args": { + "External id": 1439775,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853978224.558, "dur": 22.242, + "args": { + "External id": 1439776,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978228.240, "dur": 3.418, + "args": { + "External id": 1439777,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853978248.858, "dur": 28.267, + "args": { + "External id": 1439778,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978278.870, "dur": 19.364, + "args": { + "External id": 1439779,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853978301.761, "dur": 16.307, + "args": { + "External id": 1439780,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978319.590, "dur": 17.942, + "args": { + "External id": 1439781,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853978339.779, "dur": 24.342, + "args": { + "External id": 1439782,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978342.706, "dur": 1.659, + "args": { + "External id": 1439783,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978346.671, "dur": 0.912, + "args": { + "External id": 1439784,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978367.682, "dur": 15.051, + "args": { + "External id": 1439785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978383.889, "dur": 12.949, + "args": { + "External id": 1439786,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853978407.089, "dur": 2.675, + "args": { + "External id": 1439787,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853978421.766, "dur": 6.189, + "args": { + "External id": 1439788,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978426.405, "dur": 0.730, + "args": { + "External id": 1439789,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853978511.701, "dur": 69.537, + "args": { + "External id": 1439790,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853978587.461, "dur": 5.275, + "args": { + "External id": 1439791,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978590.752, "dur": 0.795, + "args": { + "External id": 1439792,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978596.657, "dur": 30.611, + "args": { + "External id": 1439793,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853978633.276, "dur": 5.787, + "args": { + "External id": 1439794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853978634.843, "dur": 3.512, + "args": { + "External id": 1439795,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978637.102, "dur": 1.023, + "args": { + "External id": 1439796,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853978642.308, "dur": 49.187, + "args": { + "External id": 1439797,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853978643.502, "dur": 47.161, + "args": { + "External id": 1439798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978695.860, "dur": 18.095, + "args": { + "External id": 1439799,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853978723.263, "dur": 4.566, + "args": { + "External id": 1439800,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978726.321, "dur": 0.568, + "args": { + "External id": 1439801,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853978732.644, "dur": 52.018, + "args": { + "External id": 1439802,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853978733.750, "dur": 3.984, + "args": { + "External id": 1439803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853978734.628, "dur": 2.451, + "args": { + "External id": 1439804,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978736.074, "dur": 0.856, + "args": { + "External id": 1439805,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853978741.091, "dur": 42.970, + "args": { + "External id": 1439806,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853978741.689, "dur": 41.674, + "args": { + "External id": 1439807,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853978789.146, "dur": 4.726, + "args": { + "External id": 1439808,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978791.839, "dur": 0.670, + "args": { + "External id": 1439809,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853978800.026, "dur": 1.557, + "args": { + "External id": 1439810,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853978810.631, "dur": 8.579, + "args": { + "External id": 1439811,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853978815.285, "dur": 3.642, + "args": { + "External id": 1439812,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853978918.035, "dur": 272.717, + "args": { + "External id": 1439813,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853978919.996, "dur": 3.818, + "args": { + "External id": 1439814,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853978925.530, "dur": 264.650, + "args": { + "External id": 1439815,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853978926.897, "dur": 0.371, + "args": { + "External id": 1439816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853978928.469, "dur": 23.980, + "args": { + "External id": 1439817,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853978954.182, "dur": 4.049, + "args": { + "External id": 1439818,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853978957.162, "dur": 0.843, + "args": { + "External id": 1439819,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853978959.034, "dur": 45.072, + "args": { + "External id": 1439820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853978960.544, "dur": 1.369, + "args": { + "External id": 1439821,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853978963.470, "dur": 39.917, + "args": { + "External id": 1439822,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853978966.299, "dur": 2.742, + "args": { + "External id": 1439823,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853979006.427, "dur": 27.600, + "args": { + "External id": 1439824,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979035.788, "dur": 53.389, + "args": { + "External id": 1439825,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853979095.295, "dur": 21.511, + "args": { + "External id": 1439826,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979118.352, "dur": 15.594, + "args": { + "External id": 1439827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853979136.731, "dur": 24.433, + "args": { + "External id": 1439828,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979140.084, "dur": 2.052, + "args": { + "External id": 1439829,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979144.829, "dur": 0.699, + "args": { + "External id": 1439830,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979162.557, "dur": 13.214, + "args": { + "External id": 1439831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979176.930, "dur": 11.927, + "args": { + "External id": 1439832,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853979199.927, "dur": 2.930, + "args": { + "External id": 1439833,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853979215.428, "dur": 4.972, + "args": { + "External id": 1439834,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979218.920, "dur": 0.508, + "args": { + "External id": 1439835,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853979308.173, "dur": 75.616, + "args": { + "External id": 1439836,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853979390.385, "dur": 5.208, + "args": { + "External id": 1439837,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979393.782, "dur": 0.642, + "args": { + "External id": 1439838,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979397.492, "dur": 30.261, + "args": { + "External id": 1439839,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853979433.289, "dur": 8.118, + "args": { + "External id": 1439840,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853979435.335, "dur": 5.240, + "args": { + "External id": 1439841,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979439.506, "dur": 0.857, + "args": { + "External id": 1439842,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853979445.125, "dur": 47.737, + "args": { + "External id": 1439843,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853979446.469, "dur": 45.538, + "args": { + "External id": 1439844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979497.787, "dur": 16.349, + "args": { + "External id": 1439845,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853979521.003, "dur": 4.026, + "args": { + "External id": 1439846,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979523.362, "dur": 0.676, + "args": { + "External id": 1439847,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853979530.068, "dur": 54.578, + "args": { + "External id": 1439848,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853979532.985, "dur": 4.345, + "args": { + "External id": 1439849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853979533.890, "dur": 2.735, + "args": { + "External id": 1439850,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979535.875, "dur": 0.605, + "args": { + "External id": 1439851,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853979538.106, "dur": 45.998, + "args": { + "External id": 1439852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853979538.924, "dur": 44.306, + "args": { + "External id": 1439853,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853979589.990, "dur": 4.376, + "args": { + "External id": 1439854,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979592.746, "dur": 0.431, + "args": { + "External id": 1439855,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853979601.262, "dur": 1.558, + "args": { + "External id": 1439856,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853979613.484, "dur": 6.805, + "args": { + "External id": 1439857,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853979616.137, "dur": 3.833, + "args": { + "External id": 1439858,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853979722.818, "dur": 251.914, + "args": { + "External id": 1439859,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853979725.329, "dur": 2.176, + "args": { + "External id": 1439860,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853979728.778, "dur": 245.375, + "args": { + "External id": 1439861,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853979730.163, "dur": 0.633, + "args": { + "External id": 1439862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853979733.991, "dur": 24.727, + "args": { + "External id": 1439863,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853979760.548, "dur": 3.946, + "args": { + "External id": 1439864,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979763.225, "dur": 1.047, + "args": { + "External id": 1439865,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853979765.479, "dur": 25.769, + "args": { + "External id": 1439866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853979766.910, "dur": 1.342, + "args": { + "External id": 1439867,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853979769.548, "dur": 21.217, + "args": { + "External id": 1439868,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979772.978, "dur": 3.207, + "args": { + "External id": 1439869,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853979792.825, "dur": 24.794, + "args": { + "External id": 1439870,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979819.336, "dur": 17.825, + "args": { + "External id": 1439871,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853979880.847, "dur": 19.291, + "args": { + "External id": 1439872,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979901.570, "dur": 17.071, + "args": { + "External id": 1439873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853979921.057, "dur": 24.204, + "args": { + "External id": 1439874,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979923.925, "dur": 1.641, + "args": { + "External id": 1439875,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853979928.216, "dur": 0.766, + "args": { + "External id": 1439876,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979946.753, "dur": 13.630, + "args": { + "External id": 1439877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853979961.325, "dur": 11.688, + "args": { + "External id": 1439878,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853980003.075, "dur": 2.953, + "args": { + "External id": 1439879,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853980019.474, "dur": 5.181, + "args": { + "External id": 1439880,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980023.196, "dur": 0.610, + "args": { + "External id": 1439881,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853980152.975, "dur": 72.704, + "args": { + "External id": 1439882,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853980232.952, "dur": 6.496, + "args": { + "External id": 1439883,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980236.587, "dur": 1.150, + "args": { + "External id": 1439884,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980241.855, "dur": 30.870, + "args": { + "External id": 1439885,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853980278.466, "dur": 6.070, + "args": { + "External id": 1439886,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853980280.289, "dur": 3.435, + "args": { + "External id": 1439887,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980282.363, "dur": 1.111, + "args": { + "External id": 1439888,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853980287.776, "dur": 50.527, + "args": { + "External id": 1439889,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853980292.107, "dur": 45.516, + "args": { + "External id": 1439890,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980343.559, "dur": 17.525, + "args": { + "External id": 1439891,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853980368.165, "dur": 4.165, + "args": { + "External id": 1439892,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980370.726, "dur": 0.611, + "args": { + "External id": 1439893,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853980380.383, "dur": 52.721, + "args": { + "External id": 1439894,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853980381.553, "dur": 6.164, + "args": { + "External id": 1439895,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853980384.515, "dur": 2.505, + "args": { + "External id": 1439896,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980386.281, "dur": 0.597, + "args": { + "External id": 1439897,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853980388.451, "dur": 43.965, + "args": { + "External id": 1439898,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853980389.403, "dur": 42.331, + "args": { + "External id": 1439899,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853980437.817, "dur": 4.367, + "args": { + "External id": 1439900,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980440.341, "dur": 0.630, + "args": { + "External id": 1439901,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853980451.217, "dur": 1.841, + "args": { + "External id": 1439902,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853980462.804, "dur": 10.236, + "args": { + "External id": 1439903,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853980465.512, "dur": 7.220, + "args": { + "External id": 1439904,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853980573.463, "dur": 209.868, + "args": { + "External id": 1439905,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853980575.973, "dur": 2.326, + "args": { + "External id": 1439906,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853980580.499, "dur": 202.300, + "args": { + "External id": 1439907,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853980583.277, "dur": 0.516, + "args": { + "External id": 1439908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853980585.735, "dur": 23.906, + "args": { + "External id": 1439909,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853980612.076, "dur": 4.195, + "args": { + "External id": 1439910,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980614.872, "dur": 1.160, + "args": { + "External id": 1439911,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853980617.533, "dur": 25.412, + "args": { + "External id": 1439912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853980618.869, "dur": 1.338, + "args": { + "External id": 1439913,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853980621.901, "dur": 20.698, + "args": { + "External id": 1439914,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980624.755, "dur": 2.976, + "args": { + "External id": 1439915,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853980644.859, "dur": 24.558, + "args": { + "External id": 1439916,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980671.072, "dur": 17.295, + "args": { + "External id": 1439917,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853980691.221, "dur": 16.456, + "args": { + "External id": 1439918,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980709.304, "dur": 14.972, + "args": { + "External id": 1439919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853980726.382, "dur": 23.168, + "args": { + "External id": 1439920,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980729.184, "dur": 1.706, + "args": { + "External id": 1439921,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980733.212, "dur": 0.790, + "args": { + "External id": 1439922,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980751.440, "dur": 14.928, + "args": { + "External id": 1439923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980767.887, "dur": 13.839, + "args": { + "External id": 1439924,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853980790.514, "dur": 1.640, + "args": { + "External id": 1439925,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853980801.827, "dur": 4.570, + "args": { + "External id": 1439926,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980804.901, "dur": 0.584, + "args": { + "External id": 1439927,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853980878.911, "dur": 58.221, + "args": { + "External id": 1439928,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853980943.022, "dur": 5.240, + "args": { + "External id": 1439929,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853980946.235, "dur": 0.958, + "args": { + "External id": 1439930,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853980949.790, "dur": 47.473, + "args": { + "External id": 1439931,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853981004.994, "dur": 7.201, + "args": { + "External id": 1439932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853981007.378, "dur": 3.860, + "args": { + "External id": 1439933,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981009.903, "dur": 1.103, + "args": { + "External id": 1439934,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853981017.264, "dur": 107.903, + "args": { + "External id": 1439935,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853981018.623, "dur": 104.969, + "args": { + "External id": 1439936,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981132.298, "dur": 18.434, + "args": { + "External id": 1439937,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853981158.594, "dur": 5.512, + "args": { + "External id": 1439938,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981161.824, "dur": 1.056, + "args": { + "External id": 1439939,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853981169.200, "dur": 58.804, + "args": { + "External id": 1439940,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853981170.537, "dur": 5.975, + "args": { + "External id": 1439941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853981173.056, "dur": 2.775, + "args": { + "External id": 1439942,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981174.986, "dur": 0.671, + "args": { + "External id": 1439943,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853981177.458, "dur": 50.076, + "args": { + "External id": 1439944,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853981178.478, "dur": 48.372, + "args": { + "External id": 1439945,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853981232.999, "dur": 4.379, + "args": { + "External id": 1439946,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981235.488, "dur": 0.584, + "args": { + "External id": 1439947,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853981245.038, "dur": 1.816, + "args": { + "External id": 1439948,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853981257.574, "dur": 7.118, + "args": { + "External id": 1439949,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853981260.341, "dur": 4.017, + "args": { + "External id": 1439950,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853981370.060, "dur": 209.766, + "args": { + "External id": 1439951,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853981372.896, "dur": 2.409, + "args": { + "External id": 1439952,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853981377.192, "dur": 202.134, + "args": { + "External id": 1439953,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853981378.585, "dur": 0.687, + "args": { + "External id": 1439954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853981380.860, "dur": 27.161, + "args": { + "External id": 1439955,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853981409.733, "dur": 3.975, + "args": { + "External id": 1439956,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981412.756, "dur": 0.666, + "args": { + "External id": 1439957,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853981414.652, "dur": 31.005, + "args": { + "External id": 1439958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853981415.832, "dur": 1.460, + "args": { + "External id": 1439959,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853981418.750, "dur": 26.437, + "args": { + "External id": 1439960,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981423.704, "dur": 3.327, + "args": { + "External id": 1439961,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853981447.296, "dur": 23.452, + "args": { + "External id": 1439962,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981472.554, "dur": 16.253, + "args": { + "External id": 1439963,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853981492.164, "dur": 16.616, + "args": { + "External id": 1439964,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981510.242, "dur": 15.745, + "args": { + "External id": 1439965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853981528.088, "dur": 22.703, + "args": { + "External id": 1439966,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981531.187, "dur": 1.935, + "args": { + "External id": 1439967,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981535.281, "dur": 0.784, + "args": { + "External id": 1439968,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981552.395, "dur": 13.262, + "args": { + "External id": 1439969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981566.865, "dur": 11.273, + "args": { + "External id": 1439970,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853981587.496, "dur": 1.939, + "args": { + "External id": 1439971,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853981600.068, "dur": 4.240, + "args": { + "External id": 1439972,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981602.974, "dur": 0.444, + "args": { + "External id": 1439973,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853981676.595, "dur": 56.610, + "args": { + "External id": 1439974,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853981738.529, "dur": 5.237, + "args": { + "External id": 1439975,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981741.702, "dur": 0.801, + "args": { + "External id": 1439976,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981745.857, "dur": 35.557, + "args": { + "External id": 1439977,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853981786.305, "dur": 5.913, + "args": { + "External id": 1439978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853981788.044, "dur": 3.446, + "args": { + "External id": 1439979,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981790.113, "dur": 1.170, + "args": { + "External id": 1439980,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853981795.137, "dur": 45.170, + "args": { + "External id": 1439981,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853981796.003, "dur": 43.435, + "args": { + "External id": 1439982,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853981844.661, "dur": 18.237, + "args": { + "External id": 1439983,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853981869.339, "dur": 4.472, + "args": { + "External id": 1439984,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981872.059, "dur": 0.657, + "args": { + "External id": 1439985,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413853981878.047, "dur": 51.592, + "args": { + "External id": 1439986,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853981878.951, "dur": 4.176, + "args": { + "External id": 1439987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853981879.764, "dur": 2.783, + "args": { + "External id": 1439988,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981881.807, "dur": 0.600, + "args": { + "External id": 1439989,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853981883.910, "dur": 45.281, + "args": { + "External id": 1439990,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853981886.850, "dur": 41.733, + "args": { + "External id": 1439991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853981933.802, "dur": 4.342, + "args": { + "External id": 1439992,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853981936.271, "dur": 0.760, + "args": { + "External id": 1439993,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853981947.655, "dur": 1.488, + "args": { + "External id": 1439994,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853981957.583, "dur": 9.624, + "args": { + "External id": 1439995,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853981961.432, "dur": 5.480, + "args": { + "External id": 1439996,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853982126.527, "dur": 209.499, + "args": { + "External id": 1439997,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853982130.599, "dur": 4.065, + "args": { + "External id": 1439998,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413853982136.902, "dur": 198.554, + "args": { + "External id": 1439999,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413853982138.704, "dur": 0.424, + "args": { + "External id": 1440000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413853982140.583, "dur": 28.620, + "args": { + "External id": 1440001,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413853982171.166, "dur": 4.292, + "args": { + "External id": 1440002,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982174.311, "dur": 0.855, + "args": { + "External id": 1440003,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853982176.685, "dur": 23.229, + "args": { + "External id": 1440004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853982178.293, "dur": 1.790, + "args": { + "External id": 1440005,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413853982181.369, "dur": 18.245, + "args": { + "External id": 1440006,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982184.227, "dur": 2.927, + "args": { + "External id": 1440007,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413853982201.609, "dur": 24.254, + "args": { + "External id": 1440008,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982227.790, "dur": 18.510, + "args": { + "External id": 1440009,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413853982249.060, "dur": 17.147, + "args": { + "External id": 1440010,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982267.782, "dur": 14.952, + "args": { + "External id": 1440011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853982284.890, "dur": 20.878, + "args": { + "External id": 1440012,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982287.043, "dur": 1.527, + "args": { + "External id": 1440013,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982290.947, "dur": 0.654, + "args": { + "External id": 1440014,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982307.406, "dur": 13.329, + "args": { + "External id": 1440015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982322.063, "dur": 12.240, + "args": { + "External id": 1440016,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853982343.489, "dur": 2.537, + "args": { + "External id": 1440017,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982356.170, "dur": 4.094, + "args": { + "External id": 1440018,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982358.848, "dur": 0.527, + "args": { + "External id": 1440019,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853982436.078, "dur": 70.564, + "args": { + "External id": 1440020,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982512.532, "dur": 5.231, + "args": { + "External id": 1440021,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982515.788, "dur": 0.648, + "args": { + "External id": 1440022,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982519.282, "dur": 31.266, + "args": { + "External id": 1440023,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413853982556.124, "dur": 6.099, + "args": { + "External id": 1440024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413853982558.208, "dur": 3.313, + "args": { + "External id": 1440025,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982560.392, "dur": 0.925, + "args": { + "External id": 1440026,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413853982565.203, "dur": 47.697, + "args": { + "External id": 1440027,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413853982566.253, "dur": 45.790, + "args": { + "External id": 1440028,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982617.058, "dur": 16.906, + "args": { + "External id": 1440029,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853982639.030, "dur": 25.627, + "args": { + "External id": 1440030,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853982642.524, "dur": 21.712, + "args": { + "External id": 1440031,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982648.062, "dur": 0.572, + "args": { + "External id": 1440032,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 20324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853982670.297, "dur": 27.293, + "args": { + "External id": 1440033,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853982672.497, "dur": 24.767, + "args": { + "External id": 1440034,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 20326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982677.544, "dur": 3.769, + "args": { + "External id": 1440035,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982682.594, "dur": 14.059, + "args": { + "External id": 1440036,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853982710.328, "dur": 7.148, + "args": { + "External id": 1440037,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853982714.047, "dur": 3.021, + "args": { + "External id": 1440038,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853982718.848, "dur": 0.964, + "args": { + "External id": 1440039,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413853982719.196, "dur": 0.536, + "args": { + "External id": 1440040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982767.645, "dur": 24.054, + "args": { + "External id": 1440041,"Sequence number": 15349103, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982793.765, "dur": 14.350, + "args": { + "External id": 1440042,"Sequence number": 15349104, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20334 + } + }, + { + "ph": "s", "id": 233, "pid": 2338706, "tid": 2338706, "ts": 6413853982793.765, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982814.779, "dur": 7.153, + "args": { + "External id": 1440043,"Sequence number": 15349105, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[8, 4, 4096], [], [], [], []], "Ev Idx": 20335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982818.805, "dur": 1.463, + "args": { + "External id": 1440044,"Record function id": 0, "Concrete Inputs": ["", "[8, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 20336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853982824.935, "dur": 6.771, + "args": { + "External id": 1440045,"Sequence number": 15349105, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "3"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[8, 4, 4096], [], []], "Ev Idx": 20337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982829.764, "dur": 0.621, + "args": { + "External id": 1440046,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[8, 4, 4096], [], [], []], "Ev Idx": 20338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982833.101, "dur": 3.451, + "args": { + "External id": 1440047,"Sequence number": 15349105, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], []], "Ev Idx": 20339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982835.082, "dur": 0.729, + "args": { + "External id": 1440048,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[8, 4096], [], [], []], "Ev Idx": 20340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982842.632, "dur": 6.852, + "args": { + "External id": 1440049,"Sequence number": 15349105, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 20341 + } + }, + { + "ph": "s", "id": 232, "pid": 2338706, "tid": 2338706, "ts": 6413853982842.632, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982846.904, "dur": 1.070, + "args": { + "External id": 1440050,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 20342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982850.668, "dur": 5.140, + "args": { + "External id": 1440051,"Sequence number": 15349106, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], [], []], "Ev Idx": 20343 + } + }, + { + "ph": "s", "id": 231, "pid": 2338706, "tid": 2338706, "ts": 6413853982850.668, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982854.399, "dur": 0.411, + "args": { + "External id": 1440052,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4, 4096]", "[67108864, 16384, 4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 20344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338706, "tid": 2338706, + "ts": 6413853982856.939, "dur": 10.421, + "args": { + "External id": 1440053,"Sequence number": 15349107, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], []], "Input Dims": [[8, 4096, 4, 4096], [], []], "Ev Idx": 20345 + } + }, + { + "ph": "s", "id": 230, "pid": 2338706, "tid": 2338706, "ts": 6413853982856.939, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982863.123, "dur": 3.206, + "args": { + "External id": 1440054,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 4096, 1], [], [], []], "Input Dims": [[8, 4096, 4, 4096], [], [], []], "Ev Idx": 20346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413853982868.631, "dur": 4.812, + "args": { + "External id": 1440055,"Sequence number": 15349108, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], [], []], "Ev Idx": 20347 + } + }, + { + "ph": "s", "id": 229, "pid": 2338706, "tid": 2338706, "ts": 6413853982868.631, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853982872.024, "dur": 0.457, + "args": { + "External id": 1440056,"Record function id": 0, "Concrete Inputs": ["", "[8, 4096, 4096]", "[67108864, 16384, 1]", "12288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[67108864, 16384, 1], [], [], []], "Input Dims": [[8, 4096, 4096], [], [], []], "Ev Idx": 20348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853982878.233, "dur": 32.099, + "args": { + "External id": 1440057,"Sequence number": 15349109, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 20349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853982880.080, "dur": 29.947, + "args": { + "External id": 1440058,"Sequence number": 15349109, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 20350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853982882.935, "dur": 7.244, + "args": { + "External id": 1440059,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[8, 4096], [], [], [], [], []], "Ev Idx": 20351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853982885.474, "dur": 4.037, + "args": { + "External id": 1440060,"Record function id": 0, "Concrete Inputs": ["[8, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853982891.175, "dur": 18.270, + "args": { + "External id": 1440061,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[8, 4096], [8, 4096], []], "Ev Idx": 20353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853982940.354, "dur": 4.869, + "args": { + "External id": 1440062,"Sequence number": 15349109, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 4096]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[67108864, 16384, 1], []], "Input Dims": [[8, 4096, 4096], []], "Ev Idx": 20354 + } + }, + { + "ph": "s", "id": 228, "pid": 2338706, "tid": 2338706, "ts": 6413853982940.354, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413853982948.043, "dur": 1.378, + "args": { + "External id": 1440063,"Sequence number": 15349110, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[8, 4096], []], "Ev Idx": 20355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 2338706, "tid": 2338706, + "ts": 6413853983008.978, "dur": 45104.668, + "args": { + "External id": 1440064,"Sequence number": 15349110, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[16384, 1], [1], [4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [32768], [32000, 4096], [], [], [], [], []], "Ev Idx": 20356 + } + }, + { + "ph": "s", "id": 227, "pid": 2338706, "tid": 2338706, "ts": 6413853983008.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338706, "tid": 2338706, + "ts": 6413853983029.859, "dur": 73.437, + "args": { + "External id": 1440065,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 20357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413853983030.705, "dur": 72.318, + "args": { + "External id": 1440066,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[16384, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 20358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853983032.641, "dur": 7.064, + "args": { + "External id": 1440067,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[16384, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 20359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853983034.654, "dur": 4.377, + "args": { + "External id": 1440068,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983040.456, "dur": 61.561, + "args": { + "External id": 1440069,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [16384, 1], []], "Input Dims": [[32768, 4096], [32768, 4096], []], "Ev Idx": 20361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853983125.995, "dur": 35.902, + "args": { + "External id": 1440070,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 20362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853983127.197, "dur": 10.648, + "args": { + "External id": 1440071,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], [], []], "Ev Idx": 20363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853983132.280, "dur": 5.160, + "args": { + "External id": 1440072,"Record function id": 0, "Concrete Inputs": ["[32768, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983139.697, "dur": 21.909, + "args": { + "External id": 1440073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983141.821, "dur": 19.267, + "args": { + "External id": 1440074,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32768, 4096], []], "Ev Idx": 20366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853983166.040, "dur": 20.651, + "args": { + "External id": 1440075,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413853983167.015, "dur": 5.116, + "args": { + "External id": 1440076,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853983168.525, "dur": 3.304, + "args": { + "External id": 1440077,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983172.713, "dur": 13.742, + "args": { + "External id": 1440078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983173.219, "dur": 12.870, + "args": { + "External id": 1440079,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[4096, 1], []], "Input Dims": [[32000, 4096], []], "Ev Idx": 20371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413853983195.762, "dur": 20.748, + "args": { + "External id": 1440080,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 20372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413853983197.520, "dur": 5.872, + "args": { + "External id": 1440081,"Record function id": 0, "Concrete Inputs": ["[32768]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983204.003, "dur": 12.166, + "args": { + "External id": 1440082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[32768]], "Ev Idx": 20374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983204.926, "dur": 10.834, + "args": { + "External id": 1440083,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413853983221.961, "dur": 25.949, + "args": { + "External id": 1440084,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853983251.029, "dur": 79.416, + "args": { + "External id": 1440085,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413853983253.396, "dur": 76.454, + "args": { + "External id": 1440086,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853983258.106, "dur": 1.155, + "args": { + "External id": 1440087,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 20379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413853983260.757, "dur": 28.457, + "args": { + "External id": 1440088,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413853983262.779, "dur": 26.108, + "args": { + "External id": 1440089,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[32768], [], [], [], [], [], []], "Ev Idx": 20381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413853983266.184, "dur": 2.998, + "args": { + "External id": 1440090,"Record function id": 0, "Concrete Inputs": ["[32768]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413853983272.073, "dur": 16.375, + "args": { + "External id": 1440091,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[32768], [32768], []], "Ev Idx": 20383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413853983336.971, "dur": 37935.602, + "args": { + "External id": 1440092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 20384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413853983338.783, "dur": 37931.328, + "args": { + "External id": 1440093,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 20385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854021292.257, "dur": 13.044, + "args": { + "External id": 1440094,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854021299.793, "dur": 1.517, + "args": { + "External id": 1440095,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854021313.348, "dur": 136.252, + "args": { + "External id": 1440096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854021316.772, "dur": 8.567, + "args": { + "External id": 1440097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854021319.822, "dur": 4.545, + "args": { + "External id": 1440098,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854021323.057, "dur": 0.958, + "args": { + "External id": 1440099,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854021327.005, "dur": 121.765, + "args": { + "External id": 1440100,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854021332.638, "dur": 115.136, + "args": { + "External id": 1440101,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854021455.249, "dur": 6.602, + "args": { + "External id": 1440102,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854021458.891, "dur": 1.073, + "args": { + "External id": 1440103,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854021474.192, "dur": 4.255, + "args": { + "External id": 1440104,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854021491.845, "dur": 9.876, + "args": { + "External id": 1440105,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854021495.571, "dur": 5.792, + "args": { + "External id": 1440106,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854021689.622, "dur": 254.505, + "args": { + "External id": 1440107,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854021693.449, "dur": 5.483, + "args": { + "External id": 1440108,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854021701.063, "dur": 242.404, + "args": { + "External id": 1440109,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854021703.966, "dur": 0.612, + "args": { + "External id": 1440110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854021705.987, "dur": 32.262, + "args": { + "External id": 1440111,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854021741.366, "dur": 4.399, + "args": { + "External id": 1440112,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854021744.583, "dur": 0.862, + "args": { + "External id": 1440113,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854021746.851, "dur": 37.566, + "args": { + "External id": 1440114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854021749.031, "dur": 1.494, + "args": { + "External id": 1440115,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854021752.360, "dur": 31.689, + "args": { + "External id": 1440116,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854021757.454, "dur": 3.736, + "args": { + "External id": 1440117,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854021786.308, "dur": 28.678, + "args": { + "External id": 1440118,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854021817.494, "dur": 18.096, + "args": { + "External id": 1440119,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854021839.046, "dur": 19.852, + "args": { + "External id": 1440120,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854021860.886, "dur": 17.324, + "args": { + "External id": 1440121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854021880.953, "dur": 26.829, + "args": { + "External id": 1440122,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854021883.592, "dur": 1.889, + "args": { + "External id": 1440123,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854021889.362, "dur": 0.717, + "args": { + "External id": 1440124,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854021909.415, "dur": 16.704, + "args": { + "External id": 1440125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854021927.544, "dur": 14.823, + "args": { + "External id": 1440126,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854021952.829, "dur": 2.239, + "args": { + "External id": 1440127,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854021963.282, "dur": 5.643, + "args": { + "External id": 1440128,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854021967.159, "dur": 0.496, + "args": { + "External id": 1440129,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854022124.869, "dur": 91.497, + "args": { + "External id": 1440130,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854022225.859, "dur": 11.952, + "args": { + "External id": 1440131,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "4096", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022231.690, "dur": 1.209, + "args": { + "External id": 1440132,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022239.856, "dur": 33.017, + "args": { + "External id": 1440133,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854022279.450, "dur": 8.190, + "args": { + "External id": 1440134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854022281.640, "dur": 5.102, + "args": { + "External id": 1440135,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022285.428, "dur": 0.975, + "args": { + "External id": 1440136,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854022292.250, "dur": 51.381, + "args": { + "External id": 1440137,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854022293.780, "dur": 49.089, + "args": { + "External id": 1440138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022348.697, "dur": 18.399, + "args": { + "External id": 1440139,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854022374.767, "dur": 5.392, + "args": { + "External id": 1440140,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022378.405, "dur": 0.658, + "args": { + "External id": 1440141,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854022385.823, "dur": 62.667, + "args": { + "External id": 1440142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854022387.031, "dur": 8.960, + "args": { + "External id": 1440143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854022389.595, "dur": 5.682, + "args": { + "External id": 1440144,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022392.341, "dur": 2.776, + "args": { + "External id": 1440145,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854022400.518, "dur": 47.543, + "args": { + "External id": 1440146,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854022401.146, "dur": 46.177, + "args": { + "External id": 1440147,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854022453.278, "dur": 4.048, + "args": { + "External id": 1440148,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022455.390, "dur": 0.551, + "args": { + "External id": 1440149,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854022466.925, "dur": 2.046, + "args": { + "External id": 1440150,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854022480.369, "dur": 7.505, + "args": { + "External id": 1440151,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854022482.868, "dur": 4.647, + "args": { + "External id": 1440152,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854022609.622, "dur": 211.004, + "args": { + "External id": 1440153,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854022613.502, "dur": 2.293, + "args": { + "External id": 1440154,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854022617.855, "dur": 202.158, + "args": { + "External id": 1440155,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854022621.373, "dur": 0.553, + "args": { + "External id": 1440156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854022623.180, "dur": 27.140, + "args": { + "External id": 1440157,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854022652.169, "dur": 4.205, + "args": { + "External id": 1440158,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022654.934, "dur": 1.135, + "args": { + "External id": 1440159,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854022657.473, "dur": 26.817, + "args": { + "External id": 1440160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854022659.040, "dur": 1.330, + "args": { + "External id": 1440161,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854022662.066, "dur": 21.834, + "args": { + "External id": 1440162,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022665.985, "dur": 2.969, + "args": { + "External id": 1440163,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854022685.974, "dur": 24.899, + "args": { + "External id": 1440164,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022712.983, "dur": 17.483, + "args": { + "External id": 1440165,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854022733.421, "dur": 15.763, + "args": { + "External id": 1440166,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022750.852, "dur": 14.849, + "args": { + "External id": 1440167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854022768.060, "dur": 22.590, + "args": { + "External id": 1440168,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022770.970, "dur": 1.774, + "args": { + "External id": 1440169,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022775.095, "dur": 0.945, + "args": { + "External id": 1440170,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022792.301, "dur": 13.135, + "args": { + "External id": 1440171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854022806.910, "dur": 11.696, + "args": { + "External id": 1440172,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854022828.485, "dur": 1.797, + "args": { + "External id": 1440173,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854022840.737, "dur": 4.156, + "args": { + "External id": 1440174,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854022843.387, "dur": 0.663, + "args": { + "External id": 1440175,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "4096"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854022924.902, "dur": 76.695, + "args": { + "External id": 1440176,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854023009.876, "dur": 6.950, + "args": { + "External id": 1440177,"Record function id": 0, "Concrete Inputs": ["", "0", "4096", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023013.881, "dur": 1.222, + "args": { + "External id": 1440178,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023018.443, "dur": 31.334, + "args": { + "External id": 1440179,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854023093.834, "dur": 10.944, + "args": { + "External id": 1440180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854023097.054, "dur": 6.752, + "args": { + "External id": 1440181,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023102.071, "dur": 1.301, + "args": { + "External id": 1440182,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854023108.351, "dur": 58.149, + "args": { + "External id": 1440183,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854023109.842, "dur": 55.904, + "args": { + "External id": 1440184,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023171.357, "dur": 21.111, + "args": { + "External id": 1440185,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854023199.861, "dur": 5.024, + "args": { + "External id": 1440186,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023202.833, "dur": 0.855, + "args": { + "External id": 1440187,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854023211.366, "dur": 53.626, + "args": { + "External id": 1440188,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854023212.641, "dur": 3.957, + "args": { + "External id": 1440189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854023213.382, "dur": 2.548, + "args": { + "External id": 1440190,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023215.012, "dur": 0.724, + "args": { + "External id": 1440191,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854023217.263, "dur": 47.332, + "args": { + "External id": 1440192,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854023218.189, "dur": 45.718, + "args": { + "External id": 1440193,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854023270.193, "dur": 4.539, + "args": { + "External id": 1440194,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023272.672, "dur": 0.655, + "args": { + "External id": 1440195,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854023283.586, "dur": 1.735, + "args": { + "External id": 1440196,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854023295.246, "dur": 8.877, + "args": { + "External id": 1440197,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854023297.364, "dur": 6.476, + "args": { + "External id": 1440198,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854023420.340, "dur": 219.149, + "args": { + "External id": 1440199,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854023422.960, "dur": 3.411, + "args": { + "External id": 1440200,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854023428.263, "dur": 210.728, + "args": { + "External id": 1440201,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854023431.714, "dur": 0.417, + "args": { + "External id": 1440202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854023433.520, "dur": 35.437, + "args": { + "External id": 1440203,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854023471.055, "dur": 4.035, + "args": { + "External id": 1440204,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023474.114, "dur": 0.666, + "args": { + "External id": 1440205,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854023476.177, "dur": 28.280, + "args": { + "External id": 1440206,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854023477.714, "dur": 1.396, + "args": { + "External id": 1440207,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854023480.828, "dur": 23.194, + "args": { + "External id": 1440208,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023484.665, "dur": 3.649, + "args": { + "External id": 1440209,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854023506.241, "dur": 25.993, + "args": { + "External id": 1440210,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023534.094, "dur": 17.581, + "args": { + "External id": 1440211,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854023555.092, "dur": 16.552, + "args": { + "External id": 1440212,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023573.441, "dur": 13.377, + "args": { + "External id": 1440213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854023589.108, "dur": 21.510, + "args": { + "External id": 1440214,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023591.488, "dur": 1.441, + "args": { + "External id": 1440215,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023595.702, "dur": 0.829, + "args": { + "External id": 1440216,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023612.391, "dur": 12.541, + "args": { + "External id": 1440217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023626.113, "dur": 11.661, + "args": { + "External id": 1440218,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854023647.151, "dur": 1.890, + "args": { + "External id": 1440219,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854023660.379, "dur": 6.218, + "args": { + "External id": 1440220,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023663.856, "dur": 1.733, + "args": { + "External id": 1440221,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854023746.109, "dur": 62.113, + "args": { + "External id": 1440222,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854023815.892, "dur": 5.012, + "args": { + "External id": 1440223,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "12288", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023818.760, "dur": 0.897, + "args": { + "External id": 1440224,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023822.641, "dur": 29.890, + "args": { + "External id": 1440225,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854023857.456, "dur": 5.836, + "args": { + "External id": 1440226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854023859.252, "dur": 3.267, + "args": { + "External id": 1440227,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023861.523, "dur": 0.746, + "args": { + "External id": 1440228,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854023871.621, "dur": 46.808, + "args": { + "External id": 1440229,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854023872.673, "dur": 44.921, + "args": { + "External id": 1440230,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854023923.051, "dur": 15.921, + "args": { + "External id": 1440231,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854023945.712, "dur": 4.500, + "args": { + "External id": 1440232,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023948.626, "dur": 0.512, + "args": { + "External id": 1440233,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854023954.827, "dur": 72.406, + "args": { + "External id": 1440234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854023955.664, "dur": 5.377, + "args": { + "External id": 1440235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854023958.087, "dur": 2.306, + "args": { + "External id": 1440236,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854023959.803, "dur": 0.416, + "args": { + "External id": 1440237,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854023961.815, "dur": 64.775, + "args": { + "External id": 1440238,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854023962.328, "dur": 63.004, + "args": { + "External id": 1440239,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854024033.923, "dur": 5.394, + "args": { + "External id": 1440240,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024036.966, "dur": 0.807, + "args": { + "External id": 1440241,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854024048.461, "dur": 2.011, + "args": { + "External id": 1440242,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854024100.612, "dur": 11.458, + "args": { + "External id": 1440243,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854024103.311, "dur": 8.181, + "args": { + "External id": 1440244,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854024222.247, "dur": 301.436, + "args": { + "External id": 1440245,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854024225.081, "dur": 2.113, + "args": { + "External id": 1440246,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854024228.658, "dur": 294.262, + "args": { + "External id": 1440247,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854024231.510, "dur": 0.416, + "args": { + "External id": 1440248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854024233.394, "dur": 26.050, + "args": { + "External id": 1440249,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854024261.553, "dur": 4.870, + "args": { + "External id": 1440250,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024264.854, "dur": 1.237, + "args": { + "External id": 1440251,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854024267.415, "dur": 23.986, + "args": { + "External id": 1440252,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854024268.844, "dur": 1.272, + "args": { + "External id": 1440253,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854024271.718, "dur": 19.229, + "args": { + "External id": 1440254,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024275.072, "dur": 2.777, + "args": { + "External id": 1440255,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854024293.104, "dur": 23.007, + "args": { + "External id": 1440256,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024416.845, "dur": 18.191, + "args": { + "External id": 1440257,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854024438.716, "dur": 14.427, + "args": { + "External id": 1440258,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024454.809, "dur": 14.043, + "args": { + "External id": 1440259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854024471.176, "dur": 22.116, + "args": { + "External id": 1440260,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024473.719, "dur": 1.893, + "args": { + "External id": 1440261,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024477.707, "dur": 0.619, + "args": { + "External id": 1440262,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024495.136, "dur": 13.108, + "args": { + "External id": 1440263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024509.799, "dur": 11.903, + "args": { + "External id": 1440264,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854024534.650, "dur": 2.695, + "args": { + "External id": 1440265,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854024549.057, "dur": 4.469, + "args": { + "External id": 1440266,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024552.121, "dur": 0.396, + "args": { + "External id": 1440267,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "12288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854024634.624, "dur": 72.897, + "args": { + "External id": 1440268,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854024714.132, "dur": 5.893, + "args": { + "External id": 1440269,"Record function id": 0, "Concrete Inputs": ["", "0", "12288", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024717.833, "dur": 0.799, + "args": { + "External id": 1440270,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024721.752, "dur": 31.273, + "args": { + "External id": 1440271,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854024758.745, "dur": 8.010, + "args": { + "External id": 1440272,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854024760.680, "dur": 5.244, + "args": { + "External id": 1440273,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024764.892, "dur": 0.792, + "args": { + "External id": 1440274,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854024770.405, "dur": 49.685, + "args": { + "External id": 1440275,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854024771.352, "dur": 47.880, + "args": { + "External id": 1440276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854024825.064, "dur": 16.936, + "args": { + "External id": 1440277,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854024848.583, "dur": 4.558, + "args": { + "External id": 1440278,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024851.622, "dur": 0.512, + "args": { + "External id": 1440279,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854024860.289, "dur": 50.435, + "args": { + "External id": 1440280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854024861.420, "dur": 3.543, + "args": { + "External id": 1440281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854024861.973, "dur": 2.329, + "args": { + "External id": 1440282,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024863.580, "dur": 0.560, + "args": { + "External id": 1440283,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854024865.617, "dur": 44.716, + "args": { + "External id": 1440284,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854024866.160, "dur": 43.406, + "args": { + "External id": 1440285,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854024915.818, "dur": 4.574, + "args": { + "External id": 1440286,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854024918.502, "dur": 0.461, + "args": { + "External id": 1440287,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854024927.951, "dur": 1.779, + "args": { + "External id": 1440288,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854024938.873, "dur": 6.327, + "args": { + "External id": 1440289,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854024940.933, "dur": 3.954, + "args": { + "External id": 1440290,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854025113.564, "dur": 218.007, + "args": { + "External id": 1440291,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854025117.193, "dur": 3.663, + "args": { + "External id": 1440292,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854025123.057, "dur": 207.926, + "args": { + "External id": 1440293,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854025125.928, "dur": 0.464, + "args": { + "External id": 1440294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854025128.368, "dur": 28.423, + "args": { + "External id": 1440295,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854025158.602, "dur": 4.190, + "args": { + "External id": 1440296,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025161.558, "dur": 0.924, + "args": { + "External id": 1440297,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854025163.735, "dur": 27.125, + "args": { + "External id": 1440298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854025165.505, "dur": 1.370, + "args": { + "External id": 1440299,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854025168.589, "dur": 21.814, + "args": { + "External id": 1440300,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025172.037, "dur": 3.500, + "args": { + "External id": 1440301,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854025192.657, "dur": 26.506, + "args": { + "External id": 1440302,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025221.019, "dur": 15.622, + "args": { + "External id": 1440303,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854025240.448, "dur": 17.489, + "args": { + "External id": 1440304,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025259.747, "dur": 15.734, + "args": { + "External id": 1440305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854025277.694, "dur": 23.343, + "args": { + "External id": 1440306,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025280.388, "dur": 1.431, + "args": { + "External id": 1440307,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025284.406, "dur": 0.542, + "args": { + "External id": 1440308,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025302.663, "dur": 13.942, + "args": { + "External id": 1440309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025317.794, "dur": 12.151, + "args": { + "External id": 1440310,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854025339.845, "dur": 2.346, + "args": { + "External id": 1440311,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854025355.504, "dur": 4.295, + "args": { + "External id": 1440312,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025358.418, "dur": 0.543, + "args": { + "External id": 1440313,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854025437.372, "dur": 66.516, + "args": { + "External id": 1440314,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854025509.786, "dur": 5.023, + "args": { + "External id": 1440315,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "20480", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025512.877, "dur": 0.782, + "args": { + "External id": 1440316,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025516.925, "dur": 30.475, + "args": { + "External id": 1440317,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854025553.046, "dur": 37.562, + "args": { + "External id": 1440318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854025578.825, "dur": 10.918, + "args": { + "External id": 1440319,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025588.667, "dur": 0.861, + "args": { + "External id": 1440320,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854025594.227, "dur": 49.247, + "args": { + "External id": 1440321,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854025595.235, "dur": 47.608, + "args": { + "External id": 1440322,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025648.368, "dur": 17.902, + "args": { + "External id": 1440323,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854025673.997, "dur": 4.553, + "args": { + "External id": 1440324,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025676.878, "dur": 0.656, + "args": { + "External id": 1440325,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854025685.539, "dur": 50.261, + "args": { + "External id": 1440326,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854025686.758, "dur": 3.556, + "args": { + "External id": 1440327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854025687.398, "dur": 2.301, + "args": { + "External id": 1440328,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025688.847, "dur": 0.691, + "args": { + "External id": 1440329,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854025691.081, "dur": 44.242, + "args": { + "External id": 1440330,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854025692.099, "dur": 42.424, + "args": { + "External id": 1440331,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854025742.047, "dur": 3.698, + "args": { + "External id": 1440332,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025743.926, "dur": 0.477, + "args": { + "External id": 1440333,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854025752.435, "dur": 1.593, + "args": { + "External id": 1440334,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854025763.035, "dur": 7.862, + "args": { + "External id": 1440335,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854025765.247, "dur": 5.337, + "args": { + "External id": 1440336,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854025868.168, "dur": 272.693, + "args": { + "External id": 1440337,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854025870.649, "dur": 2.295, + "args": { + "External id": 1440338,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854025874.618, "dur": 265.726, + "args": { + "External id": 1440339,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854025875.876, "dur": 0.622, + "args": { + "External id": 1440340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854025877.987, "dur": 24.529, + "args": { + "External id": 1440341,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854025904.097, "dur": 3.772, + "args": { + "External id": 1440342,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854025906.898, "dur": 0.692, + "args": { + "External id": 1440343,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854025908.777, "dur": 24.826, + "args": { + "External id": 1440344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854025910.184, "dur": 1.185, + "args": { + "External id": 1440345,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854025912.923, "dur": 20.247, + "args": { + "External id": 1440346,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025916.049, "dur": 2.267, + "args": { + "External id": 1440347,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854025935.006, "dur": 22.185, + "args": { + "External id": 1440348,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854025959.409, "dur": 16.701, + "args": { + "External id": 1440349,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854025998.375, "dur": 20.230, + "args": { + "External id": 1440350,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026020.495, "dur": 16.873, + "args": { + "External id": 1440351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854026039.963, "dur": 64.057, + "args": { + "External id": 1440352,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026042.590, "dur": 2.055, + "args": { + "External id": 1440353,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026047.304, "dur": 0.796, + "args": { + "External id": 1440354,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026107.314, "dur": 16.908, + "args": { + "External id": 1440355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026125.511, "dur": 13.384, + "args": { + "External id": 1440356,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854026150.288, "dur": 3.057, + "args": { + "External id": 1440357,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854026164.281, "dur": 4.777, + "args": { + "External id": 1440358,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026167.331, "dur": 0.747, + "args": { + "External id": 1440359,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "20480"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854026251.582, "dur": 67.015, + "args": { + "External id": 1440360,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854026324.594, "dur": 5.222, + "args": { + "External id": 1440361,"Record function id": 0, "Concrete Inputs": ["", "0", "20480", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026327.786, "dur": 0.767, + "args": { + "External id": 1440362,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026331.362, "dur": 29.598, + "args": { + "External id": 1440363,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854026366.316, "dur": 5.924, + "args": { + "External id": 1440364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854026368.153, "dur": 3.084, + "args": { + "External id": 1440365,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026370.321, "dur": 0.723, + "args": { + "External id": 1440366,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854026375.073, "dur": 47.730, + "args": { + "External id": 1440367,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854026378.383, "dur": 43.504, + "args": { + "External id": 1440368,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026427.287, "dur": 15.431, + "args": { + "External id": 1440369,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854026449.026, "dur": 4.455, + "args": { + "External id": 1440370,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026451.774, "dur": 0.650, + "args": { + "External id": 1440371,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854026457.946, "dur": 49.643, + "args": { + "External id": 1440372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854026459.447, "dur": 5.855, + "args": { + "External id": 1440373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854026460.507, "dur": 4.074, + "args": { + "External id": 1440374,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026463.991, "dur": 0.451, + "args": { + "External id": 1440375,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854026466.189, "dur": 40.925, + "args": { + "External id": 1440376,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854026467.443, "dur": 39.135, + "args": { + "External id": 1440377,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854026512.604, "dur": 5.937, + "args": { + "External id": 1440378,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026515.180, "dur": 2.125, + "args": { + "External id": 1440379,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854026525.577, "dur": 1.291, + "args": { + "External id": 1440380,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854026535.764, "dur": 8.106, + "args": { + "External id": 1440381,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854026539.643, "dur": 3.930, + "args": { + "External id": 1440382,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854026635.382, "dur": 210.315, + "args": { + "External id": 1440383,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854026638.062, "dur": 2.107, + "args": { + "External id": 1440384,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854026641.889, "dur": 203.373, + "args": { + "External id": 1440385,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854026643.416, "dur": 0.434, + "args": { + "External id": 1440386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854026645.735, "dur": 26.182, + "args": { + "External id": 1440387,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854026673.934, "dur": 4.860, + "args": { + "External id": 1440388,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026677.764, "dur": 0.712, + "args": { + "External id": 1440389,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854026679.730, "dur": 24.712, + "args": { + "External id": 1440390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854026681.247, "dur": 1.228, + "args": { + "External id": 1440391,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854026683.878, "dur": 20.081, + "args": { + "External id": 1440392,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026687.214, "dur": 3.181, + "args": { + "External id": 1440393,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854026706.118, "dur": 24.123, + "args": { + "External id": 1440394,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026731.890, "dur": 16.257, + "args": { + "External id": 1440395,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854026750.841, "dur": 17.031, + "args": { + "External id": 1440396,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026772.917, "dur": 15.395, + "args": { + "External id": 1440397,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854026790.437, "dur": 24.212, + "args": { + "External id": 1440398,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026793.333, "dur": 1.774, + "args": { + "External id": 1440399,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026797.886, "dur": 0.515, + "args": { + "External id": 1440400,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026816.186, "dur": 14.084, + "args": { + "External id": 1440401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854026831.407, "dur": 12.754, + "args": { + "External id": 1440402,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854026852.004, "dur": 1.901, + "args": { + "External id": 1440403,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854026863.704, "dur": 4.176, + "args": { + "External id": 1440404,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854026866.470, "dur": 0.514, + "args": { + "External id": 1440405,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854026936.388, "dur": 78.565, + "args": { + "External id": 1440406,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854027023.074, "dur": 8.720, + "args": { + "External id": 1440407,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "28672", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027029.101, "dur": 0.957, + "args": { + "External id": 1440408,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027033.625, "dur": 72.368, + "args": { + "External id": 1440409,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854027114.072, "dur": 6.896, + "args": { + "External id": 1440410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854027116.139, "dur": 3.975, + "args": { + "External id": 1440411,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027118.753, "dur": 1.127, + "args": { + "External id": 1440412,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854027124.881, "dur": 62.380, + "args": { + "External id": 1440413,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854027127.776, "dur": 58.630, + "args": { + "External id": 1440414,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027192.332, "dur": 22.009, + "args": { + "External id": 1440415,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854027222.033, "dur": 4.776, + "args": { + "External id": 1440416,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027225.093, "dur": 0.529, + "args": { + "External id": 1440417,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338706, "tid": 2338706, + "ts": 6413854027231.568, "dur": 53.598, + "args": { + "External id": 1440418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [32000, 4096], []], "Ev Idx": 20710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854027232.885, "dur": 5.470, + "args": { + "External id": 1440419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854027233.829, "dur": 3.904, + "args": { + "External id": 1440420,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[32000, 4096], [], []], "Ev Idx": 20712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027236.932, "dur": 0.669, + "args": { + "External id": 1440421,"Record function id": 0, "Concrete Inputs": ["", "[4096, 32000]", "[1, 4096]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32000, 4096], [], [], []], "Ev Idx": 20713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854027239.142, "dur": 45.658, + "args": { + "External id": 1440422,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854027240.229, "dur": 43.796, + "args": { + "External id": 1440423,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[4096, 1], [1, 4096]], "Input Dims": [[4096, 4096], [4096, 32000]], "Ev Idx": 20715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854027289.528, "dur": 4.631, + "args": { + "External id": 1440424,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027291.875, "dur": 0.841, + "args": { + "External id": 1440425,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854027301.951, "dur": 1.889, + "args": { + "External id": 1440426,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[4096, 32000], []], "Ev Idx": 20718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854027314.855, "dur": 7.713, + "args": { + "External id": 1440427,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[4096, 32000], [], [], [], [], []], "Ev Idx": 20719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854027317.186, "dur": 5.057, + "args": { + "External id": 1440428,"Record function id": 0, "Concrete Inputs": ["[4096, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854027435.084, "dur": 217.632, + "args": { + "External id": 1440429,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854027438.295, "dur": 4.121, + "args": { + "External id": 1440430,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 2338706, "tid": 2338706, + "ts": 6413854027444.067, "dur": 208.145, + "args": { + "External id": 1440431,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[4096, 1], [], [], [0]], "Ev Idx": 20723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 2338706, "tid": 2338706, + "ts": 6413854027445.633, "dur": 0.458, + "args": { + "External id": 1440432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 2338706, "tid": 2338706, + "ts": 6413854027450.157, "dur": 28.428, + "args": { + "External id": 1440433,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[4096, 1], [], []], "Ev Idx": 20725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 2338706, "tid": 2338706, + "ts": 6413854027480.632, "dur": 4.478, + "args": { + "External id": 1440434,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[4096, 1], []], "Ev Idx": 20726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027484.073, "dur": 0.760, + "args": { + "External id": 1440435,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[4096, 1], [], [], []], "Ev Idx": 20727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854027486.140, "dur": 27.253, + "args": { + "External id": 1440436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413854027488.055, "dur": 1.648, + "args": { + "External id": 1440437,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413854027491.071, "dur": 21.929, + "args": { + "External id": 1440438,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[4096], [0]], "Ev Idx": 20730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027494.836, "dur": 3.413, + "args": { + "External id": 1440439,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413854027515.514, "dur": 23.442, + "args": { + "External id": 1440440,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027540.940, "dur": 15.836, + "args": { + "External id": 1440441,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 2338706, "tid": 2338706, + "ts": 6413854027559.532, "dur": 15.352, + "args": { + "External id": 1440442,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[4096, 1], [4096, 1], []], "Ev Idx": 20734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027577.016, "dur": 18.101, + "args": { + "External id": 1440443,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[4096, 1]], "Ev Idx": 20735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854027597.796, "dur": 23.773, + "args": { + "External id": 1440444,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[4096, 1], [], [], [], [0]], "Ev Idx": 20736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027600.758, "dur": 1.593, + "args": { + "External id": 1440445,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 20737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027604.762, "dur": 0.602, + "args": { + "External id": 1440446,"Record function id": 0, "Concrete Inputs": ["", "[4096, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 20738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027623.481, "dur": 14.464, + "args": { + "External id": 1440447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[4096]], "Ev Idx": 20739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027639.080, "dur": 11.922, + "args": { + "External id": 1440448,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4096], [4096], []], "Ev Idx": 20740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413854027660.153, "dur": 1.805, + "args": { + "External id": 1440449,"Record function id": 0, "Concrete Inputs": ["", "[4096]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 20741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854027672.099, "dur": 4.368, + "args": { + "External id": 1440450,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[32768], [], [], [], []], "Ev Idx": 20742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027675.049, "dur": 0.482, + "args": { + "External id": 1440451,"Record function id": 0, "Concrete Inputs": ["", "[4096]", "[1]", "28672"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854027754.588, "dur": 57.227, + "args": { + "External id": 1440452,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [4096, 1]], "Input Dims": [[4096, 32000], [32000, 4096]], "Ev Idx": 20744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338706, "tid": 2338706, + "ts": 6413854027817.590, "dur": 5.443, + "args": { + "External id": 1440453,"Record function id": 0, "Concrete Inputs": ["", "0", "28672", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[32768, 4096], [], [], [], []], "Ev Idx": 20745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027820.903, "dur": 0.821, + "args": { + "External id": 1440454,"Record function id": 0, "Concrete Inputs": ["", "[4096, 4096]", "[4096, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[32768, 4096], [], [], []], "Ev Idx": 20746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027824.832, "dur": 28.767, + "args": { + "External id": 1440455,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[4096, 4096], [4096, 4096], []], "Ev Idx": 20747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338706, "tid": 2338706, + "ts": 6413854027858.606, "dur": 6.345, + "args": { + "External id": 1440456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[4096, 32000]], "Ev Idx": 20748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338706, "tid": 2338706, + "ts": 6413854027860.448, "dur": 3.810, + "args": { + "External id": 1440457,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[4096, 32000], [], []], "Ev Idx": 20749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027863.317, "dur": 0.738, + "args": { + "External id": 1440458,"Record function id": 0, "Concrete Inputs": ["", "[32000, 4096]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[4096, 32000], [], [], []], "Ev Idx": 20750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 2338706, "tid": 2338706, + "ts": 6413854027867.423, "dur": 44.813, + "args": { + "External id": 1440459,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338706, "tid": 2338706, + "ts": 6413854027868.258, "dur": 43.211, + "args": { + "External id": 1440460,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [4096, 1]], "Input Dims": [[32000, 4096], [4096, 4096]], "Ev Idx": 20752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854027916.445, "dur": 15.061, + "args": { + "External id": 1440461,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854027936.616, "dur": 24.010, + "args": { + "External id": 1440462,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[32768], []], "Ev Idx": 20754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338706, "tid": 2338706, + "ts": 6413854027939.450, "dur": 20.740, + "args": { + "External id": 1440463,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[32768], [], [], []], "Ev Idx": 20755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027944.795, "dur": 0.919, + "args": { + "External id": 1440464,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 20756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413854027966.548, "dur": 55.348, + "args": { + "External id": 1440465,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], []], "Ev Idx": 20757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 2338706, "tid": 2338706, + "ts": 6413854027970.810, "dur": 50.776, + "args": { + "External id": 1440466,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[32000, 4096], [], [], [], [], [], []], "Ev Idx": 20758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854027976.132, "dur": 24.145, + "args": { + "External id": 1440467,"Record function id": 0, "Concrete Inputs": ["[32000, 4096]", "[4096, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413854028003.768, "dur": 17.023, + "args": { + "External id": 1440468,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[32000, 4096], [32000, 4096], []], "Ev Idx": 20760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413854028036.138, "dur": 6.149, + "args": { + "External id": 1440469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413854028038.458, "dur": 3.503, + "args": { + "External id": 1440470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32768, 4096]], "Ev Idx": 20762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 2338706, "tid": 2338706, + "ts": 6413854028043.898, "dur": 3.226, + "args": { + "External id": 1440471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 2338706, "tid": 2338706, + "ts": 6413854028046.142, "dur": 0.749, + "args": { + "External id": 1440472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[4096, 1]], "Input Dims": [[32000, 4096]], "Ev Idx": 20764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854028140.280, "dur": 28.488, + "args": { + "External id": 1440473,"Sequence number": 15349111, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 2338706, "tid": 2338706, + "ts": 6413854028171.122, "dur": 15.573, + "args": { + "External id": 1440474,"Sequence number": 15349112, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20766 + } + }, + { + "ph": "s", "id": 226, "pid": 2338706, "tid": 2338706, "ts": 6413854028171.122, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338706, "tid": 2338706, + "ts": 6413854028310.939, "dur": 45.604, + "args": { + "External id": 1440475,"Record function id": 0, "Ev Idx": 20767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2338706, + "ts": 6413854028472.455, "dur": 38.528, + "args": { + "External id": 1440476,"Sequence number": 15349113, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 20768 + } + }, + { + "ph": "s", "id": 225, "pid": 2338706, "tid": 2338706, "ts": 6413854028472.455, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338706, "tid": 2338706, + "ts": 6413854028547.131, "dur": 33.220, + "args": { + "External id": 1440477,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 20769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413854028548.927, "dur": 11.159, + "args": { + "External id": 1440478,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 20770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413854028554.746, "dur": 4.575, + "args": { + "External id": 1440479,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413854028561.947, "dur": 17.845, + "args": { + "External id": 1440480,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 20772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2338706, + "ts": 6413856129096.100, "dur": 98.632, + "args": { + "External id": 1440481,"Sequence number": 15349114, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 20773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338706, "tid": 2338706, + "ts": 6413856129212.692, "dur": 29.113, + "args": { + "External id": 1440482,"Sequence number": 15349115, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 20774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856129256.359, "dur": 32.578, + "args": { + "External id": 1440483,"Sequence number": 15349116, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856129292.713, "dur": 193.668, + "args": { + "External id": 1440484,"Sequence number": 15349117, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 20776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856130797.539, "dur": 52.674, + "args": { + "External id": 1440485,"Sequence number": 15349118, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856130854.181, "dur": 18.827, + "args": { + "External id": 1440486,"Sequence number": 15349119, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856130885.314, "dur": 18.901, + "args": { + "External id": 1440487,"Sequence number": 15349120, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 20779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856130906.314, "dur": 15.027, + "args": { + "External id": 1440488,"Sequence number": 15349121, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 20780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 2338706, "tid": 2338706, + "ts": 6413856133776.349, "dur": 3927.429, + "args": { + "External id": 1440489,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 2338706, "tid": 2338706, + "ts": 6413856134443.847, "dur": 1553.288, + "args": { + "External id": 1440490,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 20782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 2338706, "tid": 2338706, + "ts": 6413856134467.091, "dur": 91.882, + "args": { + "External id": 1440491,"Record function id": 0, "Concrete Inputs": ["[68250]", "6", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 20783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413856134472.022, "dur": 16.317, + "args": { + "External id": 1440492,"Record function id": 0, "Concrete Inputs": ["[68250]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 20784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 2338706, "tid": 2338706, + "ts": 6413856134493.382, "dur": 64.870, + "args": { + "External id": 1440493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[68250]], "Ev Idx": 20785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 2338706, "tid": 2338706, + "ts": 6413856134497.662, "dur": 58.665, + "args": { + "External id": 1440494,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[68250], []], "Ev Idx": 20786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137743.890, "dur": 4.588, + "args": { + "External id": 1440495,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137750.704, "dur": 0.557, + "args": { + "External id": 1440496,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137752.701, "dur": 0.369, + "args": { + "External id": 1440497,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137754.527, "dur": 0.303, + "args": { + "External id": 1440498,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137756.353, "dur": 0.375, + "args": { + "External id": 1440499,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137758.209, "dur": 0.367, + "args": { + "External id": 1440500,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137760.027, "dur": 0.520, + "args": { + "External id": 1440501,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137763.275, "dur": 0.448, + "args": { + "External id": 1440502,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137764.891, "dur": 0.282, + "args": { + "External id": 1440503,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137766.498, "dur": 0.272, + "args": { + "External id": 1440504,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137768.137, "dur": 0.270, + "args": { + "External id": 1440505,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137769.594, "dur": 0.270, + "args": { + "External id": 1440506,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137771.054, "dur": 0.287, + "args": { + "External id": 1440507,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137772.536, "dur": 0.467, + "args": { + "External id": 1440508,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137774.123, "dur": 0.412, + "args": { + "External id": 1440509,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137777.398, "dur": 0.275, + "args": { + "External id": 1440510,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137778.762, "dur": 0.272, + "args": { + "External id": 1440511,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137780.302, "dur": 0.273, + "args": { + "External id": 1440512,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137781.667, "dur": 0.271, + "args": { + "External id": 1440513,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137783.258, "dur": 0.308, + "args": { + "External id": 1440514,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137784.613, "dur": 0.271, + "args": { + "External id": 1440515,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137785.938, "dur": 0.271, + "args": { + "External id": 1440516,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137787.542, "dur": 0.287, + "args": { + "External id": 1440517,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137790.534, "dur": 0.281, + "args": { + "External id": 1440518,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137791.881, "dur": 0.269, + "args": { + "External id": 1440519,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137793.561, "dur": 0.270, + "args": { + "External id": 1440520,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137795.055, "dur": 0.288, + "args": { + "External id": 1440521,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137796.346, "dur": 0.272, + "args": { + "External id": 1440522,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137797.746, "dur": 0.268, + "args": { + "External id": 1440523,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137799.152, "dur": 0.271, + "args": { + "External id": 1440524,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137800.513, "dur": 0.270, + "args": { + "External id": 1440525,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137804.027, "dur": 0.286, + "args": { + "External id": 1440526,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137805.371, "dur": 0.263, + "args": { + "External id": 1440527,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137806.815, "dur": 0.312, + "args": { + "External id": 1440528,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137808.262, "dur": 0.265, + "args": { + "External id": 1440529,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137809.563, "dur": 0.317, + "args": { + "External id": 1440530,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137810.993, "dur": 0.262, + "args": { + "External id": 1440531,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137812.247, "dur": 0.280, + "args": { + "External id": 1440532,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137813.680, "dur": 0.281, + "args": { + "External id": 1440533,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137816.438, "dur": 0.269, + "args": { + "External id": 1440534,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137817.731, "dur": 0.284, + "args": { + "External id": 1440535,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137819.302, "dur": 0.266, + "args": { + "External id": 1440536,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137821.989, "dur": 0.286, + "args": { + "External id": 1440537,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137823.349, "dur": 0.433, + "args": { + "External id": 1440538,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137824.816, "dur": 0.403, + "args": { + "External id": 1440539,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137826.289, "dur": 0.359, + "args": { + "External id": 1440540,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137827.738, "dur": 0.359, + "args": { + "External id": 1440541,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137830.991, "dur": 0.251, + "args": { + "External id": 1440542,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137832.161, "dur": 0.243, + "args": { + "External id": 1440543,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137833.521, "dur": 0.328, + "args": { + "External id": 1440544,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137834.922, "dur": 0.341, + "args": { + "External id": 1440545,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137836.169, "dur": 0.243, + "args": { + "External id": 1440546,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137837.614, "dur": 0.244, + "args": { + "External id": 1440547,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137839.306, "dur": 0.249, + "args": { + "External id": 1440548,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137840.602, "dur": 0.254, + "args": { + "External id": 1440549,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137843.627, "dur": 0.249, + "args": { + "External id": 1440550,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137844.856, "dur": 0.244, + "args": { + "External id": 1440551,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137846.051, "dur": 0.245, + "args": { + "External id": 1440552,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137847.250, "dur": 0.246, + "args": { + "External id": 1440553,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137848.472, "dur": 0.244, + "args": { + "External id": 1440554,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137849.740, "dur": 0.246, + "args": { + "External id": 1440555,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137851.336, "dur": 0.355, + "args": { + "External id": 1440556,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137853.040, "dur": 0.248, + "args": { + "External id": 1440557,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137855.926, "dur": 0.425, + "args": { + "External id": 1440558,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137857.532, "dur": 0.477, + "args": { + "External id": 1440559,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137859.226, "dur": 0.253, + "args": { + "External id": 1440560,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137860.616, "dur": 0.244, + "args": { + "External id": 1440561,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137861.804, "dur": 0.501, + "args": { + "External id": 1440562,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137863.247, "dur": 0.242, + "args": { + "External id": 1440563,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137864.423, "dur": 0.244, + "args": { + "External id": 1440564,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137865.632, "dur": 0.466, + "args": { + "External id": 1440565,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137868.982, "dur": 0.266, + "args": { + "External id": 1440566,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137870.202, "dur": 0.243, + "args": { + "External id": 1440567,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137871.425, "dur": 0.244, + "args": { + "External id": 1440568,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137872.607, "dur": 0.246, + "args": { + "External id": 1440569,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137873.780, "dur": 0.245, + "args": { + "External id": 1440570,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137874.956, "dur": 0.245, + "args": { + "External id": 1440571,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137877.076, "dur": 0.276, + "args": { + "External id": 1440572,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137878.569, "dur": 0.247, + "args": { + "External id": 1440573,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137881.743, "dur": 0.248, + "args": { + "External id": 1440574,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137883.068, "dur": 0.249, + "args": { + "External id": 1440575,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137884.300, "dur": 0.267, + "args": { + "External id": 1440576,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137885.520, "dur": 0.243, + "args": { + "External id": 1440577,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137886.908, "dur": 0.247, + "args": { + "External id": 1440578,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137888.134, "dur": 0.245, + "args": { + "External id": 1440579,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137889.392, "dur": 0.284, + "args": { + "External id": 1440580,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137890.623, "dur": 0.251, + "args": { + "External id": 1440581,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137893.350, "dur": 0.253, + "args": { + "External id": 1440582,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137894.531, "dur": 0.244, + "args": { + "External id": 1440583,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137895.893, "dur": 0.243, + "args": { + "External id": 1440584,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137897.251, "dur": 0.427, + "args": { + "External id": 1440585,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137898.807, "dur": 0.409, + "args": { + "External id": 1440586,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137900.310, "dur": 0.373, + "args": { + "External id": 1440587,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137902.742, "dur": 0.443, + "args": { + "External id": 1440588,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137904.219, "dur": 0.447, + "args": { + "External id": 1440589,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137907.450, "dur": 0.694, + "args": { + "External id": 1440590,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137909.313, "dur": 0.264, + "args": { + "External id": 1440591,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137910.648, "dur": 0.427, + "args": { + "External id": 1440592,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137912.034, "dur": 0.419, + "args": { + "External id": 1440593,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137913.389, "dur": 0.247, + "args": { + "External id": 1440594,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137914.629, "dur": 0.245, + "args": { + "External id": 1440595,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137915.996, "dur": 0.245, + "args": { + "External id": 1440596,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137917.439, "dur": 0.461, + "args": { + "External id": 1440597,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137920.949, "dur": 0.269, + "args": { + "External id": 1440598,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137922.282, "dur": 0.261, + "args": { + "External id": 1440599,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137923.636, "dur": 0.247, + "args": { + "External id": 1440600,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137924.813, "dur": 0.243, + "args": { + "External id": 1440601,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137925.980, "dur": 0.305, + "args": { + "External id": 1440602,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137927.198, "dur": 0.244, + "args": { + "External id": 1440603,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137929.007, "dur": 0.249, + "args": { + "External id": 1440604,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137930.327, "dur": 0.444, + "args": { + "External id": 1440605,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137933.867, "dur": 0.245, + "args": { + "External id": 1440606,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137935.148, "dur": 0.253, + "args": { + "External id": 1440607,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137936.463, "dur": 0.480, + "args": { + "External id": 1440608,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137937.866, "dur": 0.244, + "args": { + "External id": 1440609,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137939.205, "dur": 0.248, + "args": { + "External id": 1440610,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137940.466, "dur": 0.436, + "args": { + "External id": 1440611,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137941.862, "dur": 0.430, + "args": { + "External id": 1440612,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137943.379, "dur": 0.244, + "args": { + "External id": 1440613,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137946.954, "dur": 0.244, + "args": { + "External id": 1440614,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137948.231, "dur": 0.242, + "args": { + "External id": 1440615,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137949.402, "dur": 0.244, + "args": { + "External id": 1440616,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137950.862, "dur": 0.245, + "args": { + "External id": 1440617,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137952.069, "dur": 0.441, + "args": { + "External id": 1440618,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137953.537, "dur": 0.415, + "args": { + "External id": 1440619,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137954.876, "dur": 0.438, + "args": { + "External id": 1440620,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137956.236, "dur": 0.423, + "args": { + "External id": 1440621,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137958.870, "dur": 0.437, + "args": { + "External id": 1440622,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137960.263, "dur": 0.246, + "args": { + "External id": 1440623,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137961.917, "dur": 0.419, + "args": { + "External id": 1440624,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137963.490, "dur": 0.213, + "args": { + "External id": 1440625,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137964.717, "dur": 0.247, + "args": { + "External id": 1440626,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137965.939, "dur": 0.423, + "args": { + "External id": 1440627,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137967.334, "dur": 0.248, + "args": { + "External id": 1440628,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137968.624, "dur": 0.530, + "args": { + "External id": 1440629,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137971.369, "dur": 0.378, + "args": { + "External id": 1440630,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137972.762, "dur": 0.245, + "args": { + "External id": 1440631,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137974.039, "dur": 0.337, + "args": { + "External id": 1440632,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137975.537, "dur": 0.245, + "args": { + "External id": 1440633,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137976.830, "dur": 0.247, + "args": { + "External id": 1440634,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137977.997, "dur": 0.247, + "args": { + "External id": 1440635,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137995.194, "dur": 0.716, + "args": { + "External id": 1440636,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856137998.351, "dur": 0.457, + "args": { + "External id": 1440637,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138002.253, "dur": 0.335, + "args": { + "External id": 1440638,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138003.578, "dur": 0.277, + "args": { + "External id": 1440639,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138004.943, "dur": 0.329, + "args": { + "External id": 1440640,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138006.391, "dur": 0.248, + "args": { + "External id": 1440641,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138007.802, "dur": 0.466, + "args": { + "External id": 1440642,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138009.349, "dur": 0.369, + "args": { + "External id": 1440643,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138011.369, "dur": 0.333, + "args": { + "External id": 1440644,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138012.728, "dur": 0.595, + "args": { + "External id": 1440645,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138016.612, "dur": 0.365, + "args": { + "External id": 1440646,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138017.934, "dur": 0.269, + "args": { + "External id": 1440647,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138019.329, "dur": 0.272, + "args": { + "External id": 1440648,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138020.659, "dur": 0.479, + "args": { + "External id": 1440649,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138022.121, "dur": 0.268, + "args": { + "External id": 1440650,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138024.690, "dur": 0.266, + "args": { + "External id": 1440651,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138026.018, "dur": 0.249, + "args": { + "External id": 1440652,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138027.249, "dur": 0.251, + "args": { + "External id": 1440653,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138030.437, "dur": 0.266, + "args": { + "External id": 1440654,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138031.677, "dur": 0.265, + "args": { + "External id": 1440655,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138032.898, "dur": 0.273, + "args": { + "External id": 1440656,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138034.137, "dur": 0.267, + "args": { + "External id": 1440657,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138035.431, "dur": 0.251, + "args": { + "External id": 1440658,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138036.689, "dur": 0.251, + "args": { + "External id": 1440659,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138037.888, "dur": 0.253, + "args": { + "External id": 1440660,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138039.188, "dur": 0.253, + "args": { + "External id": 1440661,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138042.216, "dur": 0.356, + "args": { + "External id": 1440662,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138043.726, "dur": 0.269, + "args": { + "External id": 1440663,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138045.130, "dur": 0.247, + "args": { + "External id": 1440664,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138046.386, "dur": 0.364, + "args": { + "External id": 1440665,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138047.699, "dur": 0.268, + "args": { + "External id": 1440666,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138048.902, "dur": 0.404, + "args": { + "External id": 1440667,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138050.671, "dur": 0.250, + "args": { + "External id": 1440668,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138051.857, "dur": 0.243, + "args": { + "External id": 1440669,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138081.034, "dur": 1.154, + "args": { + "External id": 1440670,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138087.522, "dur": 0.493, + "args": { + "External id": 1440671,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138089.337, "dur": 0.526, + "args": { + "External id": 1440672,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138091.336, "dur": 0.280, + "args": { + "External id": 1440673,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138092.683, "dur": 0.283, + "args": { + "External id": 1440674,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138094.490, "dur": 0.461, + "args": { + "External id": 1440675,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138095.957, "dur": 0.388, + "args": { + "External id": 1440676,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138097.507, "dur": 0.372, + "args": { + "External id": 1440677,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138100.418, "dur": 0.283, + "args": { + "External id": 1440678,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138101.724, "dur": 0.282, + "args": { + "External id": 1440679,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138103.061, "dur": 0.284, + "args": { + "External id": 1440680,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138104.335, "dur": 0.283, + "args": { + "External id": 1440681,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138105.641, "dur": 0.281, + "args": { + "External id": 1440682,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138106.947, "dur": 0.282, + "args": { + "External id": 1440683,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138108.242, "dur": 0.283, + "args": { + "External id": 1440684,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138110.992, "dur": 0.353, + "args": { + "External id": 1440685,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138114.341, "dur": 0.304, + "args": { + "External id": 1440686,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138115.751, "dur": 0.253, + "args": { + "External id": 1440687,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138117.024, "dur": 0.256, + "args": { + "External id": 1440688,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138118.263, "dur": 0.256, + "args": { + "External id": 1440689,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138119.423, "dur": 0.281, + "args": { + "External id": 1440690,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138120.695, "dur": 0.258, + "args": { + "External id": 1440691,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138121.852, "dur": 0.261, + "args": { + "External id": 1440692,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138123.027, "dur": 0.260, + "args": { + "External id": 1440693,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138125.682, "dur": 0.274, + "args": { + "External id": 1440694,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138126.973, "dur": 0.259, + "args": { + "External id": 1440695,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138131.294, "dur": 0.281, + "args": { + "External id": 1440696,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138132.543, "dur": 0.257, + "args": { + "External id": 1440697,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138133.758, "dur": 0.260, + "args": { + "External id": 1440698,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138135.044, "dur": 0.410, + "args": { + "External id": 1440699,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138136.607, "dur": 0.259, + "args": { + "External id": 1440700,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138138.025, "dur": 0.380, + "args": { + "External id": 1440701,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138141.149, "dur": 0.349, + "args": { + "External id": 1440702,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138142.657, "dur": 0.258, + "args": { + "External id": 1440703,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138144.142, "dur": 0.259, + "args": { + "External id": 1440704,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138145.439, "dur": 0.256, + "args": { + "External id": 1440705,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138146.638, "dur": 0.364, + "args": { + "External id": 1440706,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138148.066, "dur": 0.270, + "args": { + "External id": 1440707,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 20999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138149.341, "dur": 0.317, + "args": { + "External id": 1440708,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138150.596, "dur": 0.368, + "args": { + "External id": 1440709,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138153.902, "dur": 0.258, + "args": { + "External id": 1440710,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138155.082, "dur": 0.256, + "args": { + "External id": 1440711,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138156.255, "dur": 0.258, + "args": { + "External id": 1440712,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138157.465, "dur": 0.258, + "args": { + "External id": 1440713,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138158.840, "dur": 0.259, + "args": { + "External id": 1440714,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138160.196, "dur": 0.257, + "args": { + "External id": 1440715,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138161.544, "dur": 0.258, + "args": { + "External id": 1440716,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138162.861, "dur": 0.398, + "args": { + "External id": 1440717,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138166.465, "dur": 0.285, + "args": { + "External id": 1440718,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138167.822, "dur": 0.504, + "args": { + "External id": 1440719,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138169.353, "dur": 0.427, + "args": { + "External id": 1440720,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138170.727, "dur": 0.258, + "args": { + "External id": 1440721,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138172.065, "dur": 0.280, + "args": { + "External id": 1440722,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138173.264, "dur": 0.258, + "args": { + "External id": 1440723,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138174.465, "dur": 0.258, + "args": { + "External id": 1440724,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138175.762, "dur": 0.258, + "args": { + "External id": 1440725,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138179.193, "dur": 0.270, + "args": { + "External id": 1440726,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138180.413, "dur": 0.261, + "args": { + "External id": 1440727,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138182.237, "dur": 0.260, + "args": { + "External id": 1440728,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138183.478, "dur": 0.364, + "args": { + "External id": 1440729,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138184.826, "dur": 0.330, + "args": { + "External id": 1440730,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138186.067, "dur": 0.275, + "args": { + "External id": 1440731,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138187.405, "dur": 0.380, + "args": { + "External id": 1440732,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138188.712, "dur": 0.400, + "args": { + "External id": 1440733,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138191.367, "dur": 0.265, + "args": { + "External id": 1440734,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138192.629, "dur": 0.258, + "args": { + "External id": 1440735,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138194.025, "dur": 0.258, + "args": { + "External id": 1440736,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138195.239, "dur": 0.358, + "args": { + "External id": 1440737,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138196.559, "dur": 0.380, + "args": { + "External id": 1440738,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138197.887, "dur": 0.259, + "args": { + "External id": 1440739,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138199.077, "dur": 0.255, + "args": { + "External id": 1440740,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138200.317, "dur": 0.277, + "args": { + "External id": 1440741,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138203.383, "dur": 0.270, + "args": { + "External id": 1440742,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138204.597, "dur": 0.257, + "args": { + "External id": 1440743,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138205.844, "dur": 0.259, + "args": { + "External id": 1440744,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138207.286, "dur": 0.257, + "args": { + "External id": 1440745,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138208.489, "dur": 0.278, + "args": { + "External id": 1440746,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138209.796, "dur": 0.276, + "args": { + "External id": 1440747,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138210.999, "dur": 0.305, + "args": { + "External id": 1440748,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138212.366, "dur": 0.265, + "args": { + "External id": 1440749,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138214.799, "dur": 0.279, + "args": { + "External id": 1440750,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138216.254, "dur": 0.261, + "args": { + "External id": 1440751,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138217.602, "dur": 0.272, + "args": { + "External id": 1440752,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138218.992, "dur": 0.256, + "args": { + "External id": 1440753,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138220.262, "dur": 0.259, + "args": { + "External id": 1440754,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138221.458, "dur": 0.479, + "args": { + "External id": 1440755,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138222.852, "dur": 0.467, + "args": { + "External id": 1440756,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138224.437, "dur": 0.257, + "args": { + "External id": 1440757,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138227.560, "dur": 0.266, + "args": { + "External id": 1440758,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138228.792, "dur": 0.259, + "args": { + "External id": 1440759,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138229.962, "dur": 0.283, + "args": { + "External id": 1440760,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138231.426, "dur": 0.259, + "args": { + "External id": 1440761,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138232.868, "dur": 0.259, + "args": { + "External id": 1440762,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138234.064, "dur": 0.256, + "args": { + "External id": 1440763,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138235.753, "dur": 0.269, + "args": { + "External id": 1440764,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138238.494, "dur": 0.285, + "args": { + "External id": 1440765,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138241.413, "dur": 0.260, + "args": { + "External id": 1440766,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856138242.579, "dur": 0.257, + "args": { + "External id": 1440767,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338706, "tid": 2338706, + "ts": 6413856138308.255, "dur": 1804.676, + "args": { + "External id": 1440768,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338706, "tid": 2338706, + "ts": 6413856138804.821, "dur": 1149.067, + "args": { + "External id": 1446913,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138813.951, "dur": 11.475, + "args": { + "External id": 1446914,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138820.897, "dur": 3.887, + "args": { + "External id": 1446915,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138826.030, "dur": 1.737, + "args": { + "External id": 1446916,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138826.998, "dur": 0.658, + "args": { + "External id": 1446917,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138828.160, "dur": 4.264, + "args": { + "External id": 1446918,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138830.438, "dur": 1.820, + "args": { + "External id": 1446919,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138832.895, "dur": 1.153, + "args": { + "External id": 1446920,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138833.379, "dur": 0.453, + "args": { + "External id": 1446921,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138834.350, "dur": 2.435, + "args": { + "External id": 1446922,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138836.101, "dur": 0.598, + "args": { + "External id": 1446923,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138837.089, "dur": 2.854, + "args": { + "External id": 1446924,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138839.240, "dur": 0.625, + "args": { + "External id": 1446925,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138841.717, "dur": 1.169, + "args": { + "External id": 1446926,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138842.198, "dur": 0.618, + "args": { + "External id": 1446927,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138843.194, "dur": 2.534, + "args": { + "External id": 1446928,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138844.818, "dur": 0.800, + "args": { + "External id": 1446929,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138845.998, "dur": 3.060, + "args": { + "External id": 1446930,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138848.198, "dur": 0.745, + "args": { + "External id": 1446931,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138849.431, "dur": 1.212, + "args": { + "External id": 1446932,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138849.862, "dur": 0.709, + "args": { + "External id": 1446933,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138850.915, "dur": 3.964, + "args": { + "External id": 1446934,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138852.862, "dur": 1.882, + "args": { + "External id": 1446935,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138855.199, "dur": 1.270, + "args": { + "External id": 1446936,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138855.657, "dur": 0.702, + "args": { + "External id": 1446937,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138856.748, "dur": 2.983, + "args": { + "External id": 1446938,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138858.951, "dur": 0.697, + "args": { + "External id": 1446939,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138860.004, "dur": 3.380, + "args": { + "External id": 1446940,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138862.628, "dur": 0.645, + "args": { + "External id": 1446941,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138864.954, "dur": 1.177, + "args": { + "External id": 1446942,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138865.409, "dur": 0.607, + "args": { + "External id": 1446943,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138866.405, "dur": 2.913, + "args": { + "External id": 1446944,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138868.572, "dur": 0.633, + "args": { + "External id": 1446945,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138869.618, "dur": 2.907, + "args": { + "External id": 1446946,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138871.685, "dur": 0.738, + "args": { + "External id": 1446947,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138872.877, "dur": 1.134, + "args": { + "External id": 1446948,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138873.305, "dur": 0.603, + "args": { + "External id": 1446949,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138874.281, "dur": 4.098, + "args": { + "External id": 1446950,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138876.374, "dur": 1.914, + "args": { + "External id": 1446951,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138878.651, "dur": 1.126, + "args": { + "External id": 1446952,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138879.075, "dur": 0.595, + "args": { + "External id": 1446953,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138880.069, "dur": 2.526, + "args": { + "External id": 1446954,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138881.862, "dur": 0.621, + "args": { + "External id": 1446955,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138882.865, "dur": 3.108, + "args": { + "External id": 1446956,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138885.065, "dur": 0.807, + "args": { + "External id": 1446957,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138887.761, "dur": 1.791, + "args": { + "External id": 1446958,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138888.203, "dur": 1.275, + "args": { + "External id": 1446959,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138889.820, "dur": 2.700, + "args": { + "External id": 1446960,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138891.686, "dur": 0.723, + "args": { + "External id": 1446961,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138892.791, "dur": 2.591, + "args": { + "External id": 1446962,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138894.698, "dur": 0.577, + "args": { + "External id": 1446963,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138895.651, "dur": 1.150, + "args": { + "External id": 1446964,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138896.095, "dur": 0.629, + "args": { + "External id": 1446965,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138897.068, "dur": 4.303, + "args": { + "External id": 1446966,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138899.192, "dur": 2.093, + "args": { + "External id": 1446967,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138901.643, "dur": 0.977, + "args": { + "External id": 1446968,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138902.078, "dur": 0.466, + "args": { + "External id": 1446969,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138902.888, "dur": 2.266, + "args": { + "External id": 1446970,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138904.340, "dur": 0.705, + "args": { + "External id": 1446971,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138905.424, "dur": 2.895, + "args": { + "External id": 1446972,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138907.218, "dur": 1.014, + "args": { + "External id": 1446973,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138910.425, "dur": 1.232, + "args": { + "External id": 1446974,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138910.865, "dur": 0.720, + "args": { + "External id": 1446975,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138911.923, "dur": 2.874, + "args": { + "External id": 1446976,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138913.584, "dur": 1.095, + "args": { + "External id": 1446977,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138915.065, "dur": 3.339, + "args": { + "External id": 1446978,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138917.642, "dur": 0.652, + "args": { + "External id": 1446979,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138918.672, "dur": 1.141, + "args": { + "External id": 1446980,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138919.099, "dur": 0.612, + "args": { + "External id": 1446981,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138920.268, "dur": 4.469, + "args": { + "External id": 1446982,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138922.215, "dur": 2.315, + "args": { + "External id": 1446983,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138925.032, "dur": 1.164, + "args": { + "External id": 1446984,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138925.476, "dur": 0.636, + "args": { + "External id": 1446985,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138926.470, "dur": 2.375, + "args": { + "External id": 1446986,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138928.104, "dur": 0.658, + "args": { + "External id": 1446987,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138929.141, "dur": 3.028, + "args": { + "External id": 1446988,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138931.475, "dur": 0.582, + "args": { + "External id": 1446989,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138934.166, "dur": 1.149, + "args": { + "External id": 1446990,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138934.643, "dur": 0.562, + "args": { + "External id": 1446991,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138935.616, "dur": 2.668, + "args": { + "External id": 1446992,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138937.516, "dur": 0.659, + "args": { + "External id": 1446993,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138938.588, "dur": 2.861, + "args": { + "External id": 1446994,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138940.706, "dur": 0.638, + "args": { + "External id": 1446995,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138941.718, "dur": 1.249, + "args": { + "External id": 1446996,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138942.147, "dur": 0.717, + "args": { + "External id": 1446997,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138943.264, "dur": 3.911, + "args": { + "External id": 1446998,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138945.283, "dur": 1.775, + "args": { + "External id": 1446999,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138947.447, "dur": 1.266, + "args": { + "External id": 1447000,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138947.877, "dur": 0.730, + "args": { + "External id": 1447001,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138949.285, "dur": 2.607, + "args": { + "External id": 1447002,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138951.049, "dur": 0.763, + "args": { + "External id": 1447003,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138952.161, "dur": 2.746, + "args": { + "External id": 1447004,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138954.098, "dur": 0.703, + "args": { + "External id": 1447005,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138957.195, "dur": 1.287, + "args": { + "External id": 1447006,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138957.663, "dur": 0.705, + "args": { + "External id": 1447007,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138958.752, "dur": 3.109, + "args": { + "External id": 1447008,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138960.587, "dur": 1.194, + "args": { + "External id": 1447009,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138962.194, "dur": 2.738, + "args": { + "External id": 1447010,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138964.258, "dur": 0.605, + "args": { + "External id": 1447011,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138965.226, "dur": 0.994, + "args": { + "External id": 1447012,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138965.672, "dur": 0.446, + "args": { + "External id": 1447013,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138966.520, "dur": 3.126, + "args": { + "External id": 1447014,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138968.347, "dur": 1.174, + "args": { + "External id": 1447015,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138969.955, "dur": 1.369, + "args": { + "External id": 1447016,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138970.399, "dur": 0.819, + "args": { + "External id": 1447017,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138971.672, "dur": 3.057, + "args": { + "External id": 1447018,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138973.921, "dur": 0.690, + "args": { + "External id": 1447019,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138975.068, "dur": 2.799, + "args": { + "External id": 1447020,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138977.030, "dur": 0.761, + "args": { + "External id": 1447021,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138994.097, "dur": 2.860, + "args": { + "External id": 1447022,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856138995.963, "dur": 0.696, + "args": { + "External id": 1447023,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856138997.409, "dur": 4.936, + "args": { + "External id": 1447024,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139000.552, "dur": 1.703, + "args": { + "External id": 1447025,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139002.636, "dur": 1.508, + "args": { + "External id": 1447026,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139003.089, "dur": 0.975, + "args": { + "External id": 1447027,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139004.468, "dur": 1.196, + "args": { + "External id": 1447028,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139004.944, "dur": 0.629, + "args": { + "External id": 1447029,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139006.042, "dur": 4.550, + "args": { + "External id": 1447030,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139009.562, "dur": 0.952, + "args": { + "External id": 1447031,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139010.944, "dur": 1.103, + "args": { + "External id": 1447032,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139011.379, "dur": 0.594, + "args": { + "External id": 1447033,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139012.332, "dur": 2.806, + "args": { + "External id": 1447034,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139014.332, "dur": 0.695, + "args": { + "External id": 1447035,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139015.495, "dur": 2.827, + "args": { + "External id": 1447036,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139017.420, "dur": 0.827, + "args": { + "External id": 1447037,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139021.276, "dur": 1.202, + "args": { + "External id": 1447038,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139021.745, "dur": 0.650, + "args": { + "External id": 1447039,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139022.748, "dur": 3.684, + "args": { + "External id": 1447040,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139024.251, "dur": 2.087, + "args": { + "External id": 1447041,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139026.704, "dur": 1.241, + "args": { + "External id": 1447042,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139027.118, "dur": 0.743, + "args": { + "External id": 1447043,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139028.218, "dur": 2.088, + "args": { + "External id": 1447044,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139028.649, "dur": 1.568, + "args": { + "External id": 1447045,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139030.599, "dur": 4.754, + "args": { + "External id": 1447046,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139034.631, "dur": 0.618, + "args": { + "External id": 1447047,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139035.669, "dur": 1.064, + "args": { + "External id": 1447048,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139036.133, "dur": 0.496, + "args": { + "External id": 1447049,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139037.008, "dur": 2.643, + "args": { + "External id": 1447050,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139038.973, "dur": 0.566, + "args": { + "External id": 1447051,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139039.920, "dur": 2.572, + "args": { + "External id": 1447052,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139041.644, "dur": 0.776, + "args": { + "External id": 1447053,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139044.403, "dur": 1.231, + "args": { + "External id": 1447054,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139044.884, "dur": 0.644, + "args": { + "External id": 1447055,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139045.908, "dur": 3.496, + "args": { + "External id": 1447056,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139047.818, "dur": 1.496, + "args": { + "External id": 1447057,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139049.694, "dur": 1.069, + "args": { + "External id": 1447058,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139050.130, "dur": 0.530, + "args": { + "External id": 1447059,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139051.178, "dur": 1.240, + "args": { + "External id": 1447060,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139051.645, "dur": 0.689, + "args": { + "External id": 1447061,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139052.700, "dur": 35.176, + "args": { + "External id": 1447062,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139085.568, "dur": 1.848, + "args": { + "External id": 1447063,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139088.485, "dur": 1.290, + "args": { + "External id": 1447064,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139089.101, "dur": 0.592, + "args": { + "External id": 1447065,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139090.098, "dur": 2.639, + "args": { + "External id": 1447066,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139092.000, "dur": 0.620, + "args": { + "External id": 1447067,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139093.041, "dur": 3.002, + "args": { + "External id": 1447068,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139095.280, "dur": 0.682, + "args": { + "External id": 1447069,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139098.719, "dur": 1.036, + "args": { + "External id": 1447070,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139099.234, "dur": 0.404, + "args": { + "External id": 1447071,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139100.054, "dur": 4.011, + "args": { + "External id": 1447072,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139101.947, "dur": 2.016, + "args": { + "External id": 1447073,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139104.364, "dur": 1.363, + "args": { + "External id": 1447074,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139104.800, "dur": 0.814, + "args": { + "External id": 1447075,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139106.010, "dur": 1.495, + "args": { + "External id": 1447076,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139106.437, "dur": 0.951, + "args": { + "External id": 1447077,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139107.784, "dur": 3.726, + "args": { + "External id": 1447078,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139111.003, "dur": 0.388, + "args": { + "External id": 1447079,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139111.833, "dur": 1.204, + "args": { + "External id": 1447080,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139112.254, "dur": 0.674, + "args": { + "External id": 1447081,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139113.341, "dur": 3.174, + "args": { + "External id": 1447082,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139115.511, "dur": 0.884, + "args": { + "External id": 1447083,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139116.794, "dur": 2.914, + "args": { + "External id": 1447084,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139118.782, "dur": 0.851, + "args": { + "External id": 1447085,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139121.957, "dur": 1.153, + "args": { + "External id": 1447086,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139122.413, "dur": 0.621, + "args": { + "External id": 1447087,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139123.389, "dur": 3.969, + "args": { + "External id": 1447088,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139125.338, "dur": 1.831, + "args": { + "External id": 1447089,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139127.634, "dur": 1.093, + "args": { + "External id": 1447090,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139128.078, "dur": 0.533, + "args": { + "External id": 1447091,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139129.168, "dur": 1.425, + "args": { + "External id": 1447092,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139129.585, "dur": 0.908, + "args": { + "External id": 1447093,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139130.867, "dur": 3.287, + "args": { + "External id": 1447094,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139133.220, "dur": 0.859, + "args": { + "External id": 1447095,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139134.483, "dur": 2.025, + "args": { + "External id": 1447096,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139135.525, "dur": 0.873, + "args": { + "External id": 1447097,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139136.826, "dur": 1.858, + "args": { + "External id": 1447098,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139137.813, "dur": 0.781, + "args": { + "External id": 1447099,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139138.993, "dur": 3.200, + "args": { + "External id": 1447100,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139141.493, "dur": 0.621, + "args": { + "External id": 1447101,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139143.789, "dur": 1.752, + "args": { + "External id": 1447102,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139144.812, "dur": 0.652, + "args": { + "External id": 1447103,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139145.873, "dur": 3.428, + "args": { + "External id": 1447104,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139147.381, "dur": 1.567, + "args": { + "External id": 1447105,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139149.606, "dur": 1.401, + "args": { + "External id": 1447106,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139150.340, "dur": 0.592, + "args": { + "External id": 1447107,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139151.441, "dur": 1.876, + "args": { + "External id": 1447108,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139152.567, "dur": 0.660, + "args": { + "External id": 1447109,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139153.614, "dur": 3.384, + "args": { + "External id": 1447110,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139156.350, "dur": 0.572, + "args": { + "External id": 1447111,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139157.347, "dur": 2.217, + "args": { + "External id": 1447112,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139158.704, "dur": 0.749, + "args": { + "External id": 1447113,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139160.081, "dur": 1.726, + "args": { + "External id": 1447114,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139160.994, "dur": 0.699, + "args": { + "External id": 1447115,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139162.098, "dur": 3.264, + "args": { + "External id": 1447116,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139164.638, "dur": 0.650, + "args": { + "External id": 1447117,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139167.373, "dur": 2.128, + "args": { + "External id": 1447118,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139168.681, "dur": 0.743, + "args": { + "External id": 1447119,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139169.943, "dur": 3.062, + "args": { + "External id": 1447120,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139171.354, "dur": 1.443, + "args": { + "External id": 1447121,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139173.312, "dur": 1.944, + "args": { + "External id": 1447122,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139174.551, "dur": 0.625, + "args": { + "External id": 1447123,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139175.638, "dur": 2.504, + "args": { + "External id": 1447124,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139177.236, "dur": 0.817, + "args": { + "External id": 1447125,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139178.530, "dur": 3.176, + "args": { + "External id": 1447126,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139180.977, "dur": 0.651, + "args": { + "External id": 1447127,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139182.027, "dur": 1.723, + "args": { + "External id": 1447128,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139183.126, "dur": 0.511, + "args": { + "External id": 1447129,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139184.055, "dur": 2.049, + "args": { + "External id": 1447130,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139185.071, "dur": 0.942, + "args": { + "External id": 1447131,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139186.523, "dur": 3.710, + "args": { + "External id": 1447132,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139189.403, "dur": 0.750, + "args": { + "External id": 1447133,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139191.883, "dur": 1.760, + "args": { + "External id": 1447134,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139192.805, "dur": 0.730, + "args": { + "External id": 1447135,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139193.948, "dur": 3.755, + "args": { + "External id": 1447136,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139195.164, "dur": 2.410, + "args": { + "External id": 1447137,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139198.008, "dur": 1.790, + "args": { + "External id": 1447138,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139199.021, "dur": 0.697, + "args": { + "External id": 1447139,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139200.276, "dur": 2.152, + "args": { + "External id": 1447140,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139201.650, "dur": 0.688, + "args": { + "External id": 1447141,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139202.927, "dur": 3.384, + "args": { + "External id": 1447142,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139205.454, "dur": 0.775, + "args": { + "External id": 1447143,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139206.626, "dur": 1.769, + "args": { + "External id": 1447144,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139207.744, "dur": 0.534, + "args": { + "External id": 1447145,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139208.895, "dur": 1.849, + "args": { + "External id": 1447146,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139209.763, "dur": 0.890, + "args": { + "External id": 1447147,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139211.064, "dur": 3.917, + "args": { + "External id": 1447148,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139214.400, "dur": 0.504, + "args": { + "External id": 1447149,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139216.738, "dur": 1.607, + "args": { + "External id": 1447150,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139217.599, "dur": 0.666, + "args": { + "External id": 1447151,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139218.643, "dur": 3.221, + "args": { + "External id": 1447152,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139219.750, "dur": 1.974, + "args": { + "External id": 1447153,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139222.157, "dur": 1.998, + "args": { + "External id": 1447154,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139223.375, "dur": 0.698, + "args": { + "External id": 1447155,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139224.501, "dur": 2.081, + "args": { + "External id": 1447156,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139225.784, "dur": 0.680, + "args": { + "External id": 1447157,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139226.878, "dur": 3.315, + "args": { + "External id": 1447158,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139229.719, "dur": 0.382, + "args": { + "External id": 1447159,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139230.548, "dur": 1.947, + "args": { + "External id": 1447160,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139231.798, "dur": 0.586, + "args": { + "External id": 1447161,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139232.963, "dur": 1.894, + "args": { + "External id": 1447162,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139233.829, "dur": 0.935, + "args": { + "External id": 1447163,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139235.148, "dur": 3.655, + "args": { + "External id": 1447164,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139237.808, "dur": 0.920, + "args": { + "External id": 1447165,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139240.366, "dur": 1.892, + "args": { + "External id": 1447166,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139241.397, "dur": 0.784, + "args": { + "External id": 1447167,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139242.664, "dur": 2.829, + "args": { + "External id": 1447168,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139243.791, "dur": 1.606, + "args": { + "External id": 1447169,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139245.786, "dur": 1.698, + "args": { + "External id": 1447170,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139246.751, "dur": 0.656, + "args": { + "External id": 1447171,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139247.986, "dur": 2.308, + "args": { + "External id": 1447172,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139249.573, "dur": 0.605, + "args": { + "External id": 1447173,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139250.585, "dur": 3.379, + "args": { + "External id": 1447174,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139252.939, "dur": 0.948, + "args": { + "External id": 1447175,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139254.290, "dur": 2.628, + "args": { + "External id": 1447176,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139256.023, "dur": 0.820, + "args": { + "External id": 1447177,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139257.207, "dur": 1.826, + "args": { + "External id": 1447178,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139258.031, "dur": 0.909, + "args": { + "External id": 1447179,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139259.321, "dur": 4.014, + "args": { + "External id": 1447180,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139262.313, "dur": 0.902, + "args": { + "External id": 1447181,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139265.115, "dur": 1.528, + "args": { + "External id": 1447182,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139265.898, "dur": 0.669, + "args": { + "External id": 1447183,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139266.959, "dur": 3.195, + "args": { + "External id": 1447184,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139268.075, "dur": 1.786, + "args": { + "External id": 1447185,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139270.470, "dur": 1.856, + "args": { + "External id": 1447186,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139271.215, "dur": 1.034, + "args": { + "External id": 1447187,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139272.628, "dur": 1.771, + "args": { + "External id": 1447188,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139273.603, "dur": 0.678, + "args": { + "External id": 1447189,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139274.800, "dur": 3.071, + "args": { + "External id": 1447190,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139277.104, "dur": 0.690, + "args": { + "External id": 1447191,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139278.193, "dur": 2.095, + "args": { + "External id": 1447192,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139279.511, "dur": 0.639, + "args": { + "External id": 1447193,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139280.584, "dur": 1.951, + "args": { + "External id": 1447194,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139281.671, "dur": 0.769, + "args": { + "External id": 1447195,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139282.831, "dur": 3.366, + "args": { + "External id": 1447196,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139285.347, "dur": 0.742, + "args": { + "External id": 1447197,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139288.464, "dur": 1.838, + "args": { + "External id": 1447198,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139289.536, "dur": 0.691, + "args": { + "External id": 1447199,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139290.661, "dur": 3.400, + "args": { + "External id": 1447200,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139291.863, "dur": 2.099, + "args": { + "External id": 1447201,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139294.371, "dur": 1.731, + "args": { + "External id": 1447202,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139295.249, "dur": 0.772, + "args": { + "External id": 1447203,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139296.509, "dur": 1.561, + "args": { + "External id": 1447204,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139297.462, "dur": 0.492, + "args": { + "External id": 1447205,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139298.404, "dur": 2.553, + "args": { + "External id": 1447206,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139300.262, "dur": 0.615, + "args": { + "External id": 1447207,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139301.277, "dur": 2.092, + "args": { + "External id": 1447208,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139302.602, "dur": 0.688, + "args": { + "External id": 1447209,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139303.660, "dur": 1.815, + "args": { + "External id": 1447210,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139304.484, "dur": 0.694, + "args": { + "External id": 1447211,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139305.764, "dur": 3.666, + "args": { + "External id": 1447212,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139308.719, "dur": 0.603, + "args": { + "External id": 1447213,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139311.768, "dur": 1.447, + "args": { + "External id": 1447214,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139312.557, "dur": 0.582, + "args": { + "External id": 1447215,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139313.522, "dur": 3.051, + "args": { + "External id": 1447216,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139314.601, "dur": 1.874, + "args": { + "External id": 1447217,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139316.884, "dur": 1.457, + "args": { + "External id": 1447218,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139317.800, "dur": 0.466, + "args": { + "External id": 1447219,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139318.649, "dur": 2.198, + "args": { + "External id": 1447220,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139320.190, "dur": 0.541, + "args": { + "External id": 1447221,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139321.144, "dur": 2.857, + "args": { + "External id": 1447222,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139323.290, "dur": 0.631, + "args": { + "External id": 1447223,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139324.317, "dur": 1.720, + "args": { + "External id": 1447224,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139325.331, "dur": 0.627, + "args": { + "External id": 1447225,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139326.328, "dur": 1.769, + "args": { + "External id": 1447226,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139327.198, "dur": 0.780, + "args": { + "External id": 1447227,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139328.402, "dur": 3.906, + "args": { + "External id": 1447228,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139331.542, "dur": 0.634, + "args": { + "External id": 1447229,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139335.062, "dur": 1.757, + "args": { + "External id": 1447230,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139336.019, "dur": 0.698, + "args": { + "External id": 1447231,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139337.116, "dur": 2.806, + "args": { + "External id": 1447232,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139338.447, "dur": 1.377, + "args": { + "External id": 1447233,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139340.224, "dur": 1.854, + "args": { + "External id": 1447234,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139341.500, "dur": 0.504, + "args": { + "External id": 1447235,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139342.385, "dur": 1.873, + "args": { + "External id": 1447236,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139343.385, "dur": 0.753, + "args": { + "External id": 1447237,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139344.553, "dur": 2.909, + "args": { + "External id": 1447238,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139346.605, "dur": 0.781, + "args": { + "External id": 1447239,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139347.801, "dur": 2.546, + "args": { + "External id": 1447240,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139349.189, "dur": 1.042, + "args": { + "External id": 1447241,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139350.669, "dur": 1.860, + "args": { + "External id": 1447242,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139351.725, "dur": 0.712, + "args": { + "External id": 1447243,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139352.843, "dur": 3.522, + "args": { + "External id": 1447244,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139355.555, "dur": 0.701, + "args": { + "External id": 1447245,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139358.454, "dur": 2.429, + "args": { + "External id": 1447246,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139359.829, "dur": 0.867, + "args": { + "External id": 1447247,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139361.188, "dur": 3.199, + "args": { + "External id": 1447248,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139362.090, "dur": 2.188, + "args": { + "External id": 1447249,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139364.697, "dur": 1.581, + "args": { + "External id": 1447250,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139365.510, "dur": 0.657, + "args": { + "External id": 1447251,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139366.569, "dur": 1.813, + "args": { + "External id": 1447252,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139367.589, "dur": 0.675, + "args": { + "External id": 1447253,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139368.753, "dur": 3.048, + "args": { + "External id": 1447254,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139371.088, "dur": 0.636, + "args": { + "External id": 1447255,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139372.117, "dur": 2.373, + "args": { + "External id": 1447256,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139373.680, "dur": 0.734, + "args": { + "External id": 1447257,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139374.806, "dur": 1.703, + "args": { + "External id": 1447258,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139375.599, "dur": 0.818, + "args": { + "External id": 1447259,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139376.809, "dur": 3.575, + "args": { + "External id": 1447260,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139379.626, "dur": 0.648, + "args": { + "External id": 1447261,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139382.218, "dur": 1.673, + "args": { + "External id": 1447262,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139383.109, "dur": 0.700, + "args": { + "External id": 1447263,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139384.189, "dur": 2.847, + "args": { + "External id": 1447264,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139385.536, "dur": 1.406, + "args": { + "External id": 1447265,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139387.367, "dur": 1.661, + "args": { + "External id": 1447266,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139388.442, "dur": 0.511, + "args": { + "External id": 1447267,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139389.339, "dur": 2.212, + "args": { + "External id": 1447268,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139390.536, "dur": 0.900, + "args": { + "External id": 1447269,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139391.854, "dur": 4.184, + "args": { + "External id": 1447270,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139394.698, "dur": 1.258, + "args": { + "External id": 1447271,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139396.353, "dur": 2.260, + "args": { + "External id": 1447272,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139397.719, "dur": 0.817, + "args": { + "External id": 1447273,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139398.904, "dur": 1.543, + "args": { + "External id": 1447274,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139399.658, "dur": 0.498, + "args": { + "External id": 1447275,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139400.736, "dur": 3.861, + "args": { + "External id": 1447276,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139403.549, "dur": 0.934, + "args": { + "External id": 1447277,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139406.850, "dur": 1.913, + "args": { + "External id": 1447278,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139407.837, "dur": 0.756, + "args": { + "External id": 1447279,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139409.053, "dur": 4.609, + "args": { + "External id": 1447280,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139411.912, "dur": 1.654, + "args": { + "External id": 1447281,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139414.003, "dur": 1.719, + "args": { + "External id": 1447282,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139414.776, "dur": 0.867, + "args": { + "External id": 1447283,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139416.327, "dur": 2.096, + "args": { + "External id": 1447284,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139417.253, "dur": 1.056, + "args": { + "External id": 1447285,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139418.761, "dur": 3.065, + "args": { + "External id": 1447286,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139420.977, "dur": 0.741, + "args": { + "External id": 1447287,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139422.207, "dur": 2.019, + "args": { + "External id": 1447288,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139423.373, "dur": 0.719, + "args": { + "External id": 1447289,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139424.555, "dur": 1.887, + "args": { + "External id": 1447290,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139425.487, "dur": 0.863, + "args": { + "External id": 1447291,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139426.732, "dur": 3.379, + "args": { + "External id": 1447292,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139429.396, "dur": 0.605, + "args": { + "External id": 1447293,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139432.115, "dur": 2.081, + "args": { + "External id": 1447294,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139433.445, "dur": 0.597, + "args": { + "External id": 1447295,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139434.498, "dur": 2.979, + "args": { + "External id": 1447296,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139436.102, "dur": 1.276, + "args": { + "External id": 1447297,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139437.777, "dur": 1.648, + "args": { + "External id": 1447298,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139438.720, "dur": 0.629, + "args": { + "External id": 1447299,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139439.715, "dur": 2.303, + "args": { + "External id": 1447300,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139441.118, "dur": 0.785, + "args": { + "External id": 1447301,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139442.385, "dur": 3.754, + "args": { + "External id": 1447302,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139445.373, "dur": 0.655, + "args": { + "External id": 1447303,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139446.480, "dur": 2.295, + "args": { + "External id": 1447304,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139448.084, "dur": 0.615, + "args": { + "External id": 1447305,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139449.080, "dur": 1.649, + "args": { + "External id": 1447306,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139449.826, "dur": 0.799, + "args": { + "External id": 1447307,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139451.083, "dur": 3.160, + "args": { + "External id": 1447308,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139453.483, "dur": 0.655, + "args": { + "External id": 1447309,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139456.250, "dur": 1.911, + "args": { + "External id": 1447310,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139457.218, "dur": 0.865, + "args": { + "External id": 1447311,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139458.497, "dur": 2.356, + "args": { + "External id": 1447312,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139459.514, "dur": 1.163, + "args": { + "External id": 1447313,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139461.171, "dur": 2.130, + "args": { + "External id": 1447314,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139462.117, "dur": 1.060, + "args": { + "External id": 1447315,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139463.645, "dur": 2.017, + "args": { + "External id": 1447316,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139464.786, "dur": 0.763, + "args": { + "External id": 1447317,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139465.954, "dur": 3.070, + "args": { + "External id": 1447318,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139468.146, "dur": 0.764, + "args": { + "External id": 1447319,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139469.342, "dur": 2.161, + "args": { + "External id": 1447320,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139470.612, "dur": 0.816, + "args": { + "External id": 1447321,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139471.812, "dur": 2.177, + "args": { + "External id": 1447322,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139472.684, "dur": 1.213, + "args": { + "External id": 1447323,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139474.307, "dur": 3.480, + "args": { + "External id": 1447324,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139477.024, "dur": 0.682, + "args": { + "External id": 1447325,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139480.093, "dur": 1.701, + "args": { + "External id": 1447326,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139480.929, "dur": 0.692, + "args": { + "External id": 1447327,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139482.132, "dur": 3.738, + "args": { + "External id": 1447328,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139483.671, "dur": 2.106, + "args": { + "External id": 1447329,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139486.173, "dur": 2.245, + "args": { + "External id": 1447330,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139487.443, "dur": 0.718, + "args": { + "External id": 1447331,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139488.895, "dur": 2.373, + "args": { + "External id": 1447332,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139490.096, "dur": 0.868, + "args": { + "External id": 1447333,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139491.749, "dur": 3.474, + "args": { + "External id": 1447334,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139494.544, "dur": 0.597, + "args": { + "External id": 1447335,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139495.571, "dur": 2.087, + "args": { + "External id": 1447336,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139496.926, "dur": 0.638, + "args": { + "External id": 1447337,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139498.133, "dur": 1.624, + "args": { + "External id": 1447338,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139498.893, "dur": 0.766, + "args": { + "External id": 1447339,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139500.051, "dur": 3.583, + "args": { + "External id": 1447340,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139502.870, "dur": 0.647, + "args": { + "External id": 1447341,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139505.550, "dur": 1.441, + "args": { + "External id": 1447342,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139506.322, "dur": 0.594, + "args": { + "External id": 1447343,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139507.280, "dur": 3.503, + "args": { + "External id": 1447344,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139508.466, "dur": 2.220, + "args": { + "External id": 1447345,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139511.114, "dur": 2.043, + "args": { + "External id": 1447346,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139512.223, "dur": 0.652, + "args": { + "External id": 1447347,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139513.494, "dur": 1.984, + "args": { + "External id": 1447348,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139514.792, "dur": 0.572, + "args": { + "External id": 1447349,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139515.770, "dur": 2.516, + "args": { + "External id": 1447350,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139517.629, "dur": 0.544, + "args": { + "External id": 1447351,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139518.623, "dur": 1.990, + "args": { + "External id": 1447352,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139519.715, "dur": 0.823, + "args": { + "External id": 1447353,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139520.917, "dur": 1.639, + "args": { + "External id": 1447354,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139521.686, "dur": 0.778, + "args": { + "External id": 1447355,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139522.863, "dur": 3.346, + "args": { + "External id": 1447356,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139525.317, "dur": 0.776, + "args": { + "External id": 1447357,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139527.965, "dur": 1.938, + "args": { + "External id": 1447358,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139529.084, "dur": 0.737, + "args": { + "External id": 1447359,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139530.348, "dur": 3.268, + "args": { + "External id": 1447360,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139531.351, "dur": 2.169, + "args": { + "External id": 1447361,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139533.909, "dur": 1.529, + "args": { + "External id": 1447362,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139534.664, "dur": 0.694, + "args": { + "External id": 1447363,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139535.748, "dur": 1.931, + "args": { + "External id": 1447364,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139536.769, "dur": 0.782, + "args": { + "External id": 1447365,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139537.977, "dur": 2.794, + "args": { + "External id": 1447366,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139540.003, "dur": 0.655, + "args": { + "External id": 1447367,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139541.089, "dur": 2.163, + "args": { + "External id": 1447368,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139542.518, "dur": 0.660, + "args": { + "External id": 1447369,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139543.544, "dur": 1.741, + "args": { + "External id": 1447370,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139544.489, "dur": 0.702, + "args": { + "External id": 1447371,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139545.576, "dur": 2.972, + "args": { + "External id": 1447372,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139547.814, "dur": 0.650, + "args": { + "External id": 1447373,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139550.316, "dur": 23.362, + "args": { + "External id": 1447374,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139569.249, "dur": 3.909, + "args": { + "External id": 1447375,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139574.242, "dur": 2.787, + "args": { + "External id": 1447376,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139575.350, "dur": 1.581, + "args": { + "External id": 1447377,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139577.358, "dur": 1.930, + "args": { + "External id": 1447378,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139578.371, "dur": 0.838, + "args": { + "External id": 1447379,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139579.609, "dur": 2.082, + "args": { + "External id": 1447380,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139580.628, "dur": 0.978, + "args": { + "External id": 1447381,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139582.073, "dur": 3.511, + "args": { + "External id": 1447382,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139584.502, "dur": 0.971, + "args": { + "External id": 1447383,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139585.972, "dur": 2.746, + "args": { + "External id": 1447384,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139587.341, "dur": 1.085, + "args": { + "External id": 1447385,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139589.123, "dur": 1.918, + "args": { + "External id": 1447386,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139590.056, "dur": 0.882, + "args": { + "External id": 1447387,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139591.373, "dur": 3.332, + "args": { + "External id": 1447388,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139594.054, "dur": 0.572, + "args": { + "External id": 1447389,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139596.249, "dur": 1.646, + "args": { + "External id": 1447390,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139597.229, "dur": 0.590, + "args": { + "External id": 1447391,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139598.274, "dur": 2.968, + "args": { + "External id": 1447392,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139599.475, "dur": 1.653, + "args": { + "External id": 1447393,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139601.583, "dur": 1.582, + "args": { + "External id": 1447394,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139602.423, "dur": 0.670, + "args": { + "External id": 1447395,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139603.517, "dur": 2.814, + "args": { + "External id": 1447396,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139605.441, "dur": 0.805, + "args": { + "External id": 1447397,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139606.748, "dur": 2.513, + "args": { + "External id": 1447398,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139608.638, "dur": 0.506, + "args": { + "External id": 1447399,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139609.639, "dur": 2.254, + "args": { + "External id": 1447400,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139611.305, "dur": 0.484, + "args": { + "External id": 1447401,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139612.232, "dur": 2.157, + "args": { + "External id": 1447402,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139613.183, "dur": 1.122, + "args": { + "External id": 1447403,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139614.715, "dur": 2.803, + "args": { + "External id": 1447404,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139616.829, "dur": 0.612, + "args": { + "External id": 1447405,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139619.550, "dur": 2.124, + "args": { + "External id": 1447406,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139620.694, "dur": 0.910, + "args": { + "External id": 1447407,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139621.982, "dur": 3.105, + "args": { + "External id": 1447408,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139623.358, "dur": 1.609, + "args": { + "External id": 1447409,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139625.520, "dur": 1.748, + "args": { + "External id": 1447410,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139626.425, "dur": 0.766, + "args": { + "External id": 1447411,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139627.769, "dur": 3.071, + "args": { + "External id": 1447412,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139629.439, "dur": 1.313, + "args": { + "External id": 1447413,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139631.332, "dur": 3.026, + "args": { + "External id": 1447414,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139633.598, "dur": 0.687, + "args": { + "External id": 1447415,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139634.683, "dur": 2.048, + "args": { + "External id": 1447416,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139635.996, "dur": 0.634, + "args": { + "External id": 1447417,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139637.072, "dur": 1.898, + "args": { + "External id": 1447418,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139638.096, "dur": 0.782, + "args": { + "External id": 1447419,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139639.273, "dur": 3.359, + "args": { + "External id": 1447420,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139641.833, "dur": 0.725, + "args": { + "External id": 1447421,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139644.674, "dur": 1.751, + "args": { + "External id": 1447422,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139645.716, "dur": 0.623, + "args": { + "External id": 1447423,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139646.728, "dur": 70.563, + "args": { + "External id": 1447424,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139715.052, "dur": 2.007, + "args": { + "External id": 1447425,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139717.883, "dur": 1.916, + "args": { + "External id": 1447426,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139718.922, "dur": 0.800, + "args": { + "External id": 1447427,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139720.179, "dur": 2.159, + "args": { + "External id": 1447428,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139721.631, "dur": 0.495, + "args": { + "External id": 1447429,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139722.685, "dur": 2.732, + "args": { + "External id": 1447430,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139724.699, "dur": 0.634, + "args": { + "External id": 1447431,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139725.746, "dur": 2.106, + "args": { + "External id": 1447432,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139727.093, "dur": 0.642, + "args": { + "External id": 1447433,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139728.169, "dur": 1.922, + "args": { + "External id": 1447434,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139729.272, "dur": 0.731, + "args": { + "External id": 1447435,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139730.452, "dur": 3.205, + "args": { + "External id": 1447436,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139732.839, "dur": 0.507, + "args": { + "External id": 1447437,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139735.730, "dur": 1.580, + "args": { + "External id": 1447438,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139736.496, "dur": 0.602, + "args": { + "External id": 1447439,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139737.634, "dur": 3.219, + "args": { + "External id": 1447440,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139739.166, "dur": 1.567, + "args": { + "External id": 1447441,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139741.225, "dur": 1.944, + "args": { + "External id": 1447442,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139742.213, "dur": 0.679, + "args": { + "External id": 1447443,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139743.532, "dur": 1.783, + "args": { + "External id": 1447444,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139744.739, "dur": 0.492, + "args": { + "External id": 1447445,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139745.613, "dur": 2.624, + "args": { + "External id": 1447446,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139747.589, "dur": 0.561, + "args": { + "External id": 1447447,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139748.568, "dur": 2.088, + "args": { + "External id": 1447448,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139749.803, "dur": 0.750, + "args": { + "External id": 1447449,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139751.002, "dur": 2.040, + "args": { + "External id": 1447450,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139752.058, "dur": 0.844, + "args": { + "External id": 1447451,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139753.361, "dur": 3.173, + "args": { + "External id": 1447452,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139755.850, "dur": 0.603, + "args": { + "External id": 1447453,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139758.473, "dur": 1.673, + "args": { + "External id": 1447454,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139759.366, "dur": 0.673, + "args": { + "External id": 1447455,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139760.481, "dur": 3.092, + "args": { + "External id": 1447456,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139761.426, "dur": 2.013, + "args": { + "External id": 1447457,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 2338706, "tid": 2338706, + "ts": 6413856139763.912, "dur": 1.721, + "args": { + "External id": 1447458,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856139764.873, "dur": 0.647, + "args": { + "External id": 1447459,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338706, "tid": 2338706, + "ts": 6413856139788.844, "dur": 151.786, + "args": { + "External id": 1447460,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 2338706, "tid": 2338706, + "ts": 6413856140134.082, "dur": 169.309, + "args": { + "External id": 1447461,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[273], [], [], [], []], "Ev Idx": 21609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 2338706, "tid": 2338706, + "ts": 6413856140214.616, "dur": 62.104, + "args": { + "External id": 1447462,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[273], [], [], [], []], "Ev Idx": 21610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338706, "tid": 2338706, + "ts": 6413856140234.010, "dur": 1.252, + "args": { + "External id": 1447463,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 21611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Redistribute", "pid": 2338706, "tid": 2338706, + "ts": 6413856140722.690, "dur": 1171.001, + "args": { + "External id": 1447464,"Sequence number": 15349122, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "False"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338706, "tid": 2338706, + "ts": 6413856140791.680, "dur": 69.275, + "args": { + "External id": 1447465,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856140797.966, "dur": 1.774, + "args": { + "External id": 1447466,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856140801.822, "dur": 0.641, + "args": { + "External id": 1447467,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 21615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 2338706, "tid": 2338706, + "ts": 6413856140938.212, "dur": 577.140, + "args": { + "External id": 1447468,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338706, "tid": 2338706, + "ts": 6413856140943.635, "dur": 79.416, + "args": { + "External id": 1447469,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338706, "tid": 2338706, + "ts": 6413856140948.821, "dur": 10.829, + "args": { + "External id": 1447470,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 21618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413856140953.242, "dur": 5.355, + "args": { + "External id": 1447471,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 21619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 2338706, "tid": 2338706, + "ts": 6413856140961.389, "dur": 60.729, + "args": { + "External id": 1447472,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 2338706, "tid": 2338706, + "ts": 6413856141033.776, "dur": 477.631, + "args": { + "External id": 1447473,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 21621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413856141108.971, "dur": 394.201, + "args": { + "External id": 1447474,"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": 21622, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 2338706, "tid": 2338706, + "ts": 6413856141125.951, "dur": 370.404, + "args": { + "External id": 1447475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338706, "tid": 2338706, + "ts": 6413856141605.113, "dur": 244.598, + "args": { + "External id": 1447476,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 2338706, "tid": 2338706, + "ts": 6413856141722.093, "dur": 37.781, + "args": { + "External id": 1447477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 2338706, "tid": 2338706, + "ts": 6413856141745.881, "dur": 4.566, + "args": { + "External id": 1447478,"Record function id": 0, "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": 21626, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338706, "tid": 2338706, + "ts": 6413856141792.017, "dur": 51.129, + "args": { + "External id": 1447479,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856141795.281, "dur": 1.461, + "args": { + "External id": 1447480,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856141798.569, "dur": 1.052, + "args": { + "External id": 1447481,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 21629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_ToTorchTensor", "pid": 2338706, "tid": 2338706, + "ts": 6413856141916.681, "dur": 25.648, + "args": { + "External id": 1447482,"Sequence number": 15349123, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338706, "tid": 2338706, + "ts": 6413856141928.446, "dur": 9.859, + "args": { + "External id": 1447483,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338706, "tid": 2338706, + "ts": 6413856141931.694, "dur": 6.382, + "args": { + "External id": 1447484,"Record function id": 0, "Concrete Inputs": ["", "[]"], "Input type": ["float", "ScalarList"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 2338706, "tid": 2338706, + "ts": 6413856142400.723, "dur": 47.058, + "args": { + "External id": 1447485,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "double", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reciprocal", "pid": 2338706, "tid": 2338706, + "ts": 6413856142460.184, "dur": 26.518, + "args": { + "External id": 1447486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mul", "pid": 2338706, "tid": 2338706, + "ts": 6413856142494.344, "dur": 25.453, + "args": { + "External id": 1447487,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "double"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clamp", "pid": 2338706, "tid": 2338706, + "ts": 6413856142533.451, "dur": 29.027, + "args": { + "External id": 1447488,"Record function id": 0, "Concrete Inputs": ["", "", "1."], "Input type": ["float", "", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 21636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856142537.137, "dur": 0.441, + "args": { + "External id": 1447489,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 21637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 2338706, "tid": 2338706, + "ts": 6413856142582.534, "dur": 0.481, + "args": { + "External id": 1447490,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 21638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 2338706, "tid": 2338706, + "ts": 6413856142768.813, "dur": 1208.584, + "args": { + "External id": 1447491,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 2338706, "tid": 2338706, + "ts": 6413856143279.089, "dur": 655.616, + "args": { + "External id": 1447492,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isnan", "pid": 2338706, "tid": 2338706, + "ts": 6413856144049.548, "dur": 72.725, + "args": { + "External id": 1447493,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 2338706, "tid": 2338706, + "ts": 6413856144085.056, "dur": 35.985, + "args": { + "External id": 1447494,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338706, "tid": 2338706, + "ts": 6413856144127.735, "dur": 7409.179, + "args": { + "External id": 1447495,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413856144129.857, "dur": 7406.399, + "args": { + "External id": 1447496,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413856144132.103, "dur": 7401.517, + "args": { + "External id": 1447497,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isinf", "pid": 2338706, "tid": 2338706, + "ts": 6413856151552.736, "dur": 100.777, + "args": { + "External id": 1447498,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413856151558.258, "dur": 63.747, + "args": { + "External id": 1447499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338706, "tid": 2338706, + "ts": 6413856151566.452, "dur": 6.243, + "args": { + "External id": 1447500,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 21648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 2338706, "tid": 2338706, + "ts": 6413856151577.961, "dur": 43.619, + "args": { + "External id": 1447501,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], [1]], "Input Dims": [[], [0]], "Ev Idx": 21649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 2338706, "tid": 2338706, + "ts": 6413856151590.454, "dur": 5.184, + "args": { + "External id": 1447502,"Record function id": 0, "Concrete Inputs": ["", "[]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 21650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 2338706, "tid": 2338706, + "ts": 6413856151624.041, "dur": 28.564, + "args": { + "External id": 1447503,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 2338706, "tid": 2338706, + "ts": 6413856151657.043, "dur": 44.670, + "args": { + "External id": 1447504,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 2338706, "tid": 2338706, + "ts": 6413856151658.225, "dur": 43.318, + "args": { + "External id": 1447505,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 2338706, "tid": 2338706, + "ts": 6413856151659.646, "dur": 41.560, + "args": { + "External id": 1447506,"Sequence number": 15349124, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21654 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#OptimizersContainer.step", "pid": 2338706, "tid": 2338706, + "ts": 6413856151751.246, "dur": 6810.247, + "args": { + "External id": 1447507,"Record function id": 0, "Ev Idx": 21655 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 2338706, "tid": 2338706, + "ts": 6413856151793.204, "dur": 6743.706, + "args": { + "External id": 1447508,"Record function id": 0, "Ev Idx": 21656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 2338706, "tid": 2338706, + "ts": 6413856153438.309, "dur": 261.089, + "args": { + "External id": 1447509,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153461.879, "dur": 1.495, + "args": { + "External id": 1447510,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153465.755, "dur": 0.162, + "args": { + "External id": 1447511,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153466.785, "dur": 0.315, + "args": { + "External id": 1447512,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153467.588, "dur": 0.559, + "args": { + "External id": 1447513,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153468.989, "dur": 0.106, + "args": { + "External id": 1447514,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153469.762, "dur": 0.073, + "args": { + "External id": 1447515,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153470.343, "dur": 0.246, + "args": { + "External id": 1447516,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153471.051, "dur": 0.064, + "args": { + "External id": 1447517,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153471.592, "dur": 0.363, + "args": { + "External id": 1447518,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153472.363, "dur": 0.297, + "args": { + "External id": 1447519,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153473.220, "dur": 0.404, + "args": { + "External id": 1447520,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153474.055, "dur": 0.272, + "args": { + "External id": 1447521,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153474.775, "dur": 0.072, + "args": { + "External id": 1447522,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153475.355, "dur": 0.079, + "args": { + "External id": 1447523,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153476.340, "dur": 0.063, + "args": { + "External id": 1447524,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153476.988, "dur": 0.059, + "args": { + "External id": 1447525,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153477.467, "dur": 0.105, + "args": { + "External id": 1447526,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153478.135, "dur": 0.060, + "args": { + "External id": 1447527,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153478.697, "dur": 0.078, + "args": { + "External id": 1447528,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153479.262, "dur": 0.080, + "args": { + "External id": 1447529,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153479.747, "dur": 0.080, + "args": { + "External id": 1447530,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153480.311, "dur": 0.064, + "args": { + "External id": 1447531,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153480.785, "dur": 0.066, + "args": { + "External id": 1447532,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153481.441, "dur": 0.075, + "args": { + "External id": 1447533,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153481.936, "dur": 0.253, + "args": { + "External id": 1447534,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153482.668, "dur": 0.081, + "args": { + "External id": 1447535,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153483.171, "dur": 0.084, + "args": { + "External id": 1447536,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153483.665, "dur": 0.093, + "args": { + "External id": 1447537,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153484.279, "dur": 0.113, + "args": { + "External id": 1447538,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153484.841, "dur": 0.068, + "args": { + "External id": 1447539,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153485.361, "dur": 0.107, + "args": { + "External id": 1447540,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153485.955, "dur": 0.065, + "args": { + "External id": 1447541,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153486.422, "dur": 0.276, + "args": { + "External id": 1447542,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153487.122, "dur": 0.087, + "args": { + "External id": 1447543,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153487.631, "dur": 0.080, + "args": { + "External id": 1447544,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153488.217, "dur": 0.065, + "args": { + "External id": 1447545,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153488.662, "dur": 0.073, + "args": { + "External id": 1447546,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153489.153, "dur": 0.139, + "args": { + "External id": 1447547,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153489.952, "dur": 0.302, + "args": { + "External id": 1447548,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153490.608, "dur": 0.067, + "args": { + "External id": 1447549,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153491.075, "dur": 0.091, + "args": { + "External id": 1447550,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153491.578, "dur": 0.383, + "args": { + "External id": 1447551,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153492.375, "dur": 0.273, + "args": { + "External id": 1447552,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153493.063, "dur": 0.102, + "args": { + "External id": 1447553,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153493.575, "dur": 0.081, + "args": { + "External id": 1447554,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153494.102, "dur": 0.106, + "args": { + "External id": 1447555,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153494.603, "dur": 0.064, + "args": { + "External id": 1447556,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153495.114, "dur": 0.075, + "args": { + "External id": 1447557,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153495.633, "dur": 0.268, + "args": { + "External id": 1447558,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153496.536, "dur": 0.073, + "args": { + "External id": 1447559,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153496.998, "dur": 0.077, + "args": { + "External id": 1447560,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153497.560, "dur": 0.061, + "args": { + "External id": 1447561,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153498.048, "dur": 0.074, + "args": { + "External id": 1447562,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153498.529, "dur": 0.075, + "args": { + "External id": 1447563,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153499.018, "dur": 0.073, + "args": { + "External id": 1447564,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153499.605, "dur": 0.063, + "args": { + "External id": 1447565,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153500.161, "dur": 0.080, + "args": { + "External id": 1447566,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153500.747, "dur": 0.077, + "args": { + "External id": 1447567,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153501.276, "dur": 0.074, + "args": { + "External id": 1447568,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153501.812, "dur": 0.083, + "args": { + "External id": 1447569,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153502.337, "dur": 0.105, + "args": { + "External id": 1447570,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153503.020, "dur": 0.275, + "args": { + "External id": 1447571,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153503.730, "dur": 0.298, + "args": { + "External id": 1447572,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153504.357, "dur": 0.072, + "args": { + "External id": 1447573,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153504.902, "dur": 0.073, + "args": { + "External id": 1447574,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153505.405, "dur": 0.075, + "args": { + "External id": 1447575,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153505.900, "dur": 0.077, + "args": { + "External id": 1447576,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153506.418, "dur": 0.071, + "args": { + "External id": 1447577,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153506.899, "dur": 0.076, + "args": { + "External id": 1447578,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153507.474, "dur": 0.077, + "args": { + "External id": 1447579,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153507.919, "dur": 0.110, + "args": { + "External id": 1447580,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153508.393, "dur": 0.062, + "args": { + "External id": 1447581,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153509.049, "dur": 0.076, + "args": { + "External id": 1447582,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153509.639, "dur": 0.077, + "args": { + "External id": 1447583,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153510.169, "dur": 0.076, + "args": { + "External id": 1447584,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153510.635, "dur": 0.077, + "args": { + "External id": 1447585,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153511.161, "dur": 0.073, + "args": { + "External id": 1447586,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153511.641, "dur": 0.079, + "args": { + "External id": 1447587,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153512.180, "dur": 0.068, + "args": { + "External id": 1447588,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153512.540, "dur": 0.061, + "args": { + "External id": 1447589,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153513.068, "dur": 0.076, + "args": { + "External id": 1447590,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153513.433, "dur": 0.060, + "args": { + "External id": 1447591,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153513.955, "dur": 0.077, + "args": { + "External id": 1447592,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153514.324, "dur": 0.058, + "args": { + "External id": 1447593,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153514.820, "dur": 0.073, + "args": { + "External id": 1447594,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153515.183, "dur": 0.059, + "args": { + "External id": 1447595,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153515.729, "dur": 0.074, + "args": { + "External id": 1447596,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153516.095, "dur": 0.063, + "args": { + "External id": 1447597,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153516.498, "dur": 0.077, + "args": { + "External id": 1447598,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153516.868, "dur": 0.058, + "args": { + "External id": 1447599,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153517.430, "dur": 0.064, + "args": { + "External id": 1447600,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153517.785, "dur": 0.057, + "args": { + "External id": 1447601,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153518.321, "dur": 0.068, + "args": { + "External id": 1447602,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153518.685, "dur": 0.057, + "args": { + "External id": 1447603,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153519.135, "dur": 0.074, + "args": { + "External id": 1447604,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153519.499, "dur": 0.056, + "args": { + "External id": 1447605,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153519.967, "dur": 0.071, + "args": { + "External id": 1447606,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153520.329, "dur": 0.059, + "args": { + "External id": 1447607,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153520.840, "dur": 0.071, + "args": { + "External id": 1447608,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153521.209, "dur": 0.256, + "args": { + "External id": 1447609,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153521.902, "dur": 0.100, + "args": { + "External id": 1447610,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153522.295, "dur": 0.083, + "args": { + "External id": 1447611,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153522.811, "dur": 0.111, + "args": { + "External id": 1447612,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153523.212, "dur": 0.058, + "args": { + "External id": 1447613,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153523.812, "dur": 0.074, + "args": { + "External id": 1447614,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153524.173, "dur": 0.087, + "args": { + "External id": 1447615,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153524.689, "dur": 0.086, + "args": { + "External id": 1447616,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153525.100, "dur": 0.094, + "args": { + "External id": 1447617,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153525.585, "dur": 0.296, + "args": { + "External id": 1447618,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153526.169, "dur": 0.092, + "args": { + "External id": 1447619,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153526.775, "dur": 0.174, + "args": { + "External id": 1447620,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153527.238, "dur": 0.057, + "args": { + "External id": 1447621,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153527.779, "dur": 0.076, + "args": { + "External id": 1447622,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153528.149, "dur": 0.064, + "args": { + "External id": 1447623,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153528.629, "dur": 0.076, + "args": { + "External id": 1447624,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153529.162, "dur": 0.075, + "args": { + "External id": 1447625,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153529.685, "dur": 0.080, + "args": { + "External id": 1447626,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153530.232, "dur": 0.078, + "args": { + "External id": 1447627,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153530.706, "dur": 0.105, + "args": { + "External id": 1447628,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153531.278, "dur": 0.077, + "args": { + "External id": 1447629,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153531.809, "dur": 0.305, + "args": { + "External id": 1447630,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153532.595, "dur": 0.082, + "args": { + "External id": 1447631,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153533.101, "dur": 0.078, + "args": { + "External id": 1447632,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153533.497, "dur": 0.065, + "args": { + "External id": 1447633,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153534.044, "dur": 0.077, + "args": { + "External id": 1447634,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153534.414, "dur": 0.064, + "args": { + "External id": 1447635,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153534.919, "dur": 0.073, + "args": { + "External id": 1447636,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153535.284, "dur": 0.066, + "args": { + "External id": 1447637,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153535.828, "dur": 0.066, + "args": { + "External id": 1447638,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153536.178, "dur": 0.066, + "args": { + "External id": 1447639,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153536.688, "dur": 0.079, + "args": { + "External id": 1447640,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153537.052, "dur": 0.062, + "args": { + "External id": 1447641,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153537.509, "dur": 0.075, + "args": { + "External id": 1447642,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153537.875, "dur": 0.059, + "args": { + "External id": 1447643,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153538.411, "dur": 0.073, + "args": { + "External id": 1447644,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153538.796, "dur": 0.062, + "args": { + "External id": 1447645,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153539.325, "dur": 0.078, + "args": { + "External id": 1447646,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153539.691, "dur": 0.064, + "args": { + "External id": 1447647,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153540.175, "dur": 0.069, + "args": { + "External id": 1447648,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153540.540, "dur": 0.062, + "args": { + "External id": 1447649,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153541.016, "dur": 0.076, + "args": { + "External id": 1447650,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153541.381, "dur": 0.061, + "args": { + "External id": 1447651,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153541.901, "dur": 0.069, + "args": { + "External id": 1447652,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153542.260, "dur": 0.055, + "args": { + "External id": 1447653,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153542.829, "dur": 0.076, + "args": { + "External id": 1447654,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153543.195, "dur": 0.063, + "args": { + "External id": 1447655,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153543.613, "dur": 0.077, + "args": { + "External id": 1447656,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153543.982, "dur": 0.063, + "args": { + "External id": 1447657,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153544.482, "dur": 0.078, + "args": { + "External id": 1447658,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153544.845, "dur": 0.062, + "args": { + "External id": 1447659,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153545.308, "dur": 0.073, + "args": { + "External id": 1447660,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153545.690, "dur": 0.062, + "args": { + "External id": 1447661,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153546.176, "dur": 0.077, + "args": { + "External id": 1447662,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153546.536, "dur": 0.064, + "args": { + "External id": 1447663,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153547.032, "dur": 0.074, + "args": { + "External id": 1447664,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153547.556, "dur": 0.067, + "args": { + "External id": 1447665,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153548.061, "dur": 0.076, + "args": { + "External id": 1447666,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153548.505, "dur": 0.076, + "args": { + "External id": 1447667,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153549.011, "dur": 0.074, + "args": { + "External id": 1447668,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153549.540, "dur": 0.077, + "args": { + "External id": 1447669,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153550.079, "dur": 0.076, + "args": { + "External id": 1447670,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153550.441, "dur": 0.062, + "args": { + "External id": 1447671,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153550.996, "dur": 0.063, + "args": { + "External id": 1447672,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153551.462, "dur": 0.079, + "args": { + "External id": 1447673,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153551.969, "dur": 0.078, + "args": { + "External id": 1447674,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153552.334, "dur": 0.062, + "args": { + "External id": 1447675,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153552.804, "dur": 0.072, + "args": { + "External id": 1447676,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153553.166, "dur": 0.056, + "args": { + "External id": 1447677,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153553.855, "dur": 0.076, + "args": { + "External id": 1447678,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153554.233, "dur": 0.055, + "args": { + "External id": 1447679,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153554.723, "dur": 0.075, + "args": { + "External id": 1447680,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153555.101, "dur": 0.060, + "args": { + "External id": 1447681,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153555.636, "dur": 0.073, + "args": { + "External id": 1447682,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153556.015, "dur": 0.058, + "args": { + "External id": 1447683,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153556.497, "dur": 0.076, + "args": { + "External id": 1447684,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153556.876, "dur": 0.064, + "args": { + "External id": 1447685,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153557.364, "dur": 0.071, + "args": { + "External id": 1447686,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153557.742, "dur": 0.060, + "args": { + "External id": 1447687,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153558.275, "dur": 0.056, + "args": { + "External id": 1447688,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153558.642, "dur": 0.057, + "args": { + "External id": 1447689,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153559.185, "dur": 0.063, + "args": { + "External id": 1447690,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153559.555, "dur": 0.061, + "args": { + "External id": 1447691,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153560.010, "dur": 0.080, + "args": { + "External id": 1447692,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153560.394, "dur": 0.062, + "args": { + "External id": 1447693,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153560.875, "dur": 0.079, + "args": { + "External id": 1447694,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153561.260, "dur": 0.062, + "args": { + "External id": 1447695,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153561.731, "dur": 0.075, + "args": { + "External id": 1447696,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153562.111, "dur": 0.078, + "args": { + "External id": 1447697,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153562.601, "dur": 0.098, + "args": { + "External id": 1447698,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153563.004, "dur": 0.208, + "args": { + "External id": 1447699,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153563.641, "dur": 0.221, + "args": { + "External id": 1447700,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153564.166, "dur": 0.063, + "args": { + "External id": 1447701,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153564.689, "dur": 0.080, + "args": { + "External id": 1447702,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153565.078, "dur": 0.207, + "args": { + "External id": 1447703,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153565.709, "dur": 0.098, + "args": { + "External id": 1447704,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153566.108, "dur": 0.061, + "args": { + "External id": 1447705,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153566.572, "dur": 0.077, + "args": { + "External id": 1447706,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153566.952, "dur": 0.089, + "args": { + "External id": 1447707,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153567.498, "dur": 0.071, + "args": { + "External id": 1447708,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153567.872, "dur": 0.060, + "args": { + "External id": 1447709,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153568.326, "dur": 0.070, + "args": { + "External id": 1447710,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153568.808, "dur": 0.079, + "args": { + "External id": 1447711,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153569.355, "dur": 0.073, + "args": { + "External id": 1447712,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153569.856, "dur": 0.073, + "args": { + "External id": 1447713,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153570.270, "dur": 0.079, + "args": { + "External id": 1447714,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153570.703, "dur": 0.065, + "args": { + "External id": 1447715,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153571.145, "dur": 0.077, + "args": { + "External id": 1447716,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153571.527, "dur": 0.065, + "args": { + "External id": 1447717,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153572.001, "dur": 0.076, + "args": { + "External id": 1447718,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153572.385, "dur": 0.064, + "args": { + "External id": 1447719,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153572.903, "dur": 0.073, + "args": { + "External id": 1447720,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153573.279, "dur": 0.061, + "args": { + "External id": 1447721,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153573.765, "dur": 0.072, + "args": { + "External id": 1447722,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153574.138, "dur": 0.076, + "args": { + "External id": 1447723,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153574.686, "dur": 0.077, + "args": { + "External id": 1447724,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153575.065, "dur": 0.064, + "args": { + "External id": 1447725,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153575.754, "dur": 0.078, + "args": { + "External id": 1447726,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153576.135, "dur": 0.061, + "args": { + "External id": 1447727,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153576.619, "dur": 0.071, + "args": { + "External id": 1447728,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153576.997, "dur": 0.063, + "args": { + "External id": 1447729,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153577.728, "dur": 0.061, + "args": { + "External id": 1447730,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153578.088, "dur": 0.063, + "args": { + "External id": 1447731,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153578.611, "dur": 0.078, + "args": { + "External id": 1447732,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153578.996, "dur": 0.060, + "args": { + "External id": 1447733,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153579.575, "dur": 0.080, + "args": { + "External id": 1447734,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153579.956, "dur": 0.061, + "args": { + "External id": 1447735,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153580.429, "dur": 0.077, + "args": { + "External id": 1447736,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153580.809, "dur": 0.066, + "args": { + "External id": 1447737,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153581.305, "dur": 0.075, + "args": { + "External id": 1447738,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153581.984, "dur": 0.080, + "args": { + "External id": 1447739,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153582.524, "dur": 0.063, + "args": { + "External id": 1447740,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153582.891, "dur": 0.064, + "args": { + "External id": 1447741,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153583.378, "dur": 0.072, + "args": { + "External id": 1447742,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153583.765, "dur": 0.064, + "args": { + "External id": 1447743,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153584.259, "dur": 0.083, + "args": { + "External id": 1447744,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153584.646, "dur": 0.065, + "args": { + "External id": 1447745,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153585.081, "dur": 0.080, + "args": { + "External id": 1447746,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153585.467, "dur": 0.060, + "args": { + "External id": 1447747,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153585.990, "dur": 0.078, + "args": { + "External id": 1447748,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153586.376, "dur": 0.078, + "args": { + "External id": 1447749,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153586.903, "dur": 0.073, + "args": { + "External id": 1447750,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153587.283, "dur": 0.062, + "args": { + "External id": 1447751,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153587.680, "dur": 0.077, + "args": { + "External id": 1447752,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153588.157, "dur": 0.076, + "args": { + "External id": 1447753,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153588.588, "dur": 0.077, + "args": { + "External id": 1447754,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153589.078, "dur": 0.073, + "args": { + "External id": 1447755,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153589.656, "dur": 0.079, + "args": { + "External id": 1447756,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153590.036, "dur": 0.089, + "args": { + "External id": 1447757,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153590.633, "dur": 0.074, + "args": { + "External id": 1447758,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153591.015, "dur": 0.057, + "args": { + "External id": 1447759,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153591.475, "dur": 0.075, + "args": { + "External id": 1447760,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153591.860, "dur": 0.064, + "args": { + "External id": 1447761,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153592.371, "dur": 0.077, + "args": { + "External id": 1447762,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153592.755, "dur": 0.063, + "args": { + "External id": 1447763,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153593.334, "dur": 0.078, + "args": { + "External id": 1447764,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153593.723, "dur": 0.062, + "args": { + "External id": 1447765,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153594.237, "dur": 0.077, + "args": { + "External id": 1447766,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153594.623, "dur": 0.060, + "args": { + "External id": 1447767,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153595.061, "dur": 0.076, + "args": { + "External id": 1447768,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153595.434, "dur": 0.062, + "args": { + "External id": 1447769,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153596.081, "dur": 0.073, + "args": { + "External id": 1447770,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153596.460, "dur": 0.063, + "args": { + "External id": 1447771,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153596.927, "dur": 0.076, + "args": { + "External id": 1447772,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153597.306, "dur": 0.065, + "args": { + "External id": 1447773,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153597.816, "dur": 0.079, + "args": { + "External id": 1447774,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153598.223, "dur": 0.062, + "args": { + "External id": 1447775,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153598.709, "dur": 0.074, + "args": { + "External id": 1447776,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153599.090, "dur": 0.063, + "args": { + "External id": 1447777,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153599.569, "dur": 0.074, + "args": { + "External id": 1447778,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153599.946, "dur": 0.060, + "args": { + "External id": 1447779,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153600.427, "dur": 0.080, + "args": { + "External id": 1447780,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153600.809, "dur": 0.065, + "args": { + "External id": 1447781,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 2338706, "tid": 2338706, + "ts": 6413856153601.305, "dur": 0.076, + "args": { + "External id": 1447782,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 21930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 2338706, "tid": 2338706, + "ts": 6413856154335.169, "dur": 4089.739, + "args": { + "External id": 1447783,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "3.441411894557276e-06", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 21931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 2338706, "tid": 2338706, + "ts": 6413856157126.299, "dur": 1078.014, + "args": { + "External id": 1447784,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "3.441411894557276e-06", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 21932 + } + }, + { + "name": "process_name", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 0, + "args": { + "sort_index": 2338706 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 2338706, + "args": { + "name": "thread 2338706 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 2338706, + "args": { + "sort_index": 2338706 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 2379422, + "args": { + "name": "thread 2379422 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 2379422, + "args": { + "sort_index": 2379422 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 2379422, + "args": { + "name": "thread 2379422 (pt_autograd_0)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6413849637449.433, "pid": 2338706, "tid": 2379422, + "args": { + "sort_index": 2379422 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 6413849637352.972, "dur": 6527942.092, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6413849637352.972, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 6413849637352.972 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 6413856271493.423 + } + ], + "traceName": "exp/mtp.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine/profile_trace/iteration_32768/rank0_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file